PyTorchKR Papers

최신 논문

총 1,841편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1305.4228

The state-of-the-art in web-scale semantic information processing for cloud computing

Based on integrated infrastructure of resource sharing and computing in distributed environment, cloud computing involves the provision of dynamically scalable and provides virtualized resources as services over the Internet. These applications also bring a large scale heterogeneous and distributed information which pose a great challenge in terms of the semantic ambiguity. It is critical for application services in cloud computing environment to provide users intelligent service and precise information. Semantic information processing can help users deal with semantic ambiguity and information overload efficiently through appropriate semantic models and semantic information processing technology. The semantic information processing have been successfully employed in many fields such as the knowledge representation, natural language understanding, intelligent web search, etc. The purpose of this report is to give an overview of existing technologies for semantic information processing in cloud computing environment, to propose a research direction for addressing distributed semantic reasoning and parallel semantic computing by exploiting semantic information newly available in cloud computing environment.

arXiv:1308.1507

Logical analysis of natural language semantics to solve the problem of computer understanding

An object--oriented approach to create a natural language understanding system is considered. The understanding program is a formal system built on the base of predicative calculus. Horn's clauses are used as well--formed formulas. An inference is based on the principle of resolution. Sentences of natural language are represented in the view of typical predicate set. These predicates describe physical objects and processes, abstract objects, categories and semantic relations between objects. Predicates for concrete assertions are saved in a database. To describe the semantics of classes for physical objects, abstract concepts and processes, a knowledge base is applied. The proposed representation of natural language sentences is a semantic net. Nodes of such net are typical predicates. This approach is perspective as, firstly, such typification of nodes facilitates essentially forming of processing algorithms and object descriptions, secondly, the effectiveness of algorithms is increased (particularly for the great number of nodes), thirdly, to describe the semantics of words, encyclopedic knowledge is used, and this permits essentially to extend the class of solved problems.

arXiv:1310.1425

A State of the Art of Word Sense Induction: A Way Towards Word Sense Disambiguation for Under-Resourced Languages

Word Sense Disambiguation (WSD), the process of automatically identifying the meaning of a polysemous word in a sentence, is a fundamental task in Natural Language Processing (NLP). Progress in this approach to WSD opens up many promising developments in the field of NLP and its applications. Indeed, improvement over current performance levels could allow us to take a first step towards natural language understanding. Due to the lack of lexical resources it is sometimes difficult to perform WSD for under-resourced languages. This paper is an investigation on how to initiate research in WSD for under-resourced languages by applying Word Sense Induction (WSI) and suggests some interesting topics to focus on.

arXiv:1401.6122

Identifying Bengali Multiword Expressions using Semantic Clustering

One of the key issues in both natural language understanding and generation is the appropriate processing of Multiword Expressions (MWEs). MWEs pose a huge problem to the precise language processing due to their idiosyncratic nature and diversity in lexical, syntactical and semantic properties. The semantics of a MWE cannot be expressed after combining the semantics of its constituents. Therefore, the formalism of semantic clustering is often viewed as an instrument for extracting MWEs especially for resource constraint languages like Bengali. The present semantic clustering approach contributes to locate clusters of the synonymous noun tokens present in the document. These clusters in turn help measure the similarity between the constituent words of a potentially candidate phrase using a vector space model and judge the suitability of this phrase to be a MWE. In this experiment, we apply the semantic clustering approach for noun-noun bigram MWEs, though it can be extended to any types of MWEs. In parallel, the well known statistical models, namely Point-wise Mutual Information (PMI), Log Likelihood Ratio (LLR), Significance function are also employed to extract MWEs from the Bengali corpus. The comparative evaluation shows that the semantic clustering approach outperforms all other competing statistical models. As a by-product of this experiment, we have started developing a standard lexicon in Bengali that serves as a productive Bengali linguistic thesaurus.

arXiv:1411.4109

Resolution of Difficult Pronouns Using the ROSS Method

A new natural language understanding method for disambiguation of difficult pronouns is described. Difficult pronouns are those pronouns for which a level of world or domain knowledge is needed in order to perform anaphoral or other types of resolution. Resolution of difficult pronouns may in some cases require a prior step involving the application of inference to a situation that is represented by the natural language text. A general method is described: it performs entity resolution and pronoun resolution. An extension to the general pronoun resolution method performs inference as an embedded commonsense reasoning method. The general method and the embedded method utilize features of the ROSS representational scheme; in particular the methods use ROSS ontology classes and the ROSS situation model. The overall method is a working solution that solves the following Winograd schemas: a) trophy and suitcase, b) person lifts person, c) person pays detective, and d) councilmen and demonstrators.

arXiv:1411.4194

ROSS User's Guide and Reference Manual (Version 1.0)

The ROSS method is a new approach in the area of knowledge representation that is useful for many artificial intelligence and natural language understanding representation and reasoning tasks. (ROSS stands for "Representation", "Ontology", "Structure", "Star" language). ROSS is a physical symbol-based representational scheme. ROSS provides a complex model for the declarative representation of physical structure and for the representation of processes and causality. From the metaphysical perspective, the ROSS view of external reality involves a 4D model, wherein discrete single-time-point unit-sized locations with states are the basis for all objects, processes and aspects that can be modeled. ROSS includes a language called "Star" for the specification of ontology classes. The ROSS method also includes a formal scheme called the "instance model". Instance models are used in the area of natural language meaning representation to represent situations. This document is an in-depth specification of the ROSS method.

arXiv:1503.04881

Long Short-Term Memory Over Tree Structures

The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation. In this paper, we propose to extend it to tree structures, in which a memory cell can reflect the history memories of multiple child cells or multiple descendant cells in a recursive process. We call the model S-LSTM, which provides a principled way of considering long-distance interaction over hierarchies, e.g., language or image parse structures. We leverage the models for semantic composition to understand the meaning of text, a fundamental problem in natural language understanding, and show that it outperforms a state-of-the-art recursive model by replacing its composition layers with the S-LSTM memory blocks. We also show that utilizing the given structures is helpful in achieving a performance better than that without considering the structures.

arXiv:1504.07182

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management through Dynamic Stochastic State Evolution

In this paper, we present a probabilistic framework for goal-driven spoken dialog systems. A new dynamic stochastic state (DS-state) is then defined to characterize the goal set of a dialog state at different stages of the dialog process. Furthermore, an entropy minimization dialog management(EMDM) strategy is also proposed to combine with the DS-states to facilitate a robust and efficient solution in reaching a user's goals. A Song-On-Demand task, with a total of 38117 songs and 12 attributes corresponding to each song, is used to test the performance of the proposed approach. In an ideal simulation, assuming no errors, the EMDM strategy is the most efficient goal-seeking method among all tested approaches, returning the correct song within 3.3 dialog turns on average. Furthermore, in a practical scenario, with top five candidates to handle the unavoidable automatic speech recognition (ASR) and natural language understanding (NLU) errors, the results show that only 61.7\% of the dialog goals can be successfully obtained in 6.23 dialog turns on average when random questions are asked by the system, whereas if the proposed DS-states are updated with the top 5 candidates from the SLU output using the proposed EMDM strategy executed at every DS-state, then a 86.7\% dialog success rate can be accomplished effectively within 5.17 dialog turns on average. We also demonstrate that entropy-based DM strategies are more efficient than non-entropy based DM. Moreover, using the goal set distributions in EMDM, the results are better than those without them, such as in sate-of-the-art database summary DM.

arXiv:1506.05869

A Neural Conversational Model

Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require hand-crafted rules. In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework. Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation. The strength of our model is that it can be trained end-to-end and thus requires much fewer hand-crafted rules. We find that this straightforward model can generate simple conversations given a large conversational training dataset. Our preliminary results suggest that, despite optimizing the wrong objective function, the model is able to converse well. It is able extract knowledge from both a domain specific dataset, and from a large, noisy, and general domain dataset of movie subtitles. On a domain-specific IT helpdesk dataset, the model can find a solution to a technical problem via conversations. On a noisy open-domain movie transcript dataset, the model can perform simple forms of common sense reasoning. As expected, we also find that the lack of consistency is a common failure mode of our model.

arXiv:1508.00189

Class Vectors: Embedding representation of Document Classes

Distributed representations of words and paragraphs as semantic embeddings in high dimensional data are used across a number of Natural Language Understanding tasks such as retrieval, translation, and classification. In this work, we propose "Class Vectors" - a framework for learning a vector per class in the same embedding space as the word and paragraph embeddings. Similarity between these class vectors and word vectors are used as features to classify a document to a class. In experiment on several sentiment analysis tasks such as Yelp reviews and Amazon electronic product reviews, class vectors have shown better or comparable results in classification while learning very meaningful class embeddings.

arXiv:1509.08075

Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing

We introduce Segment-Phrase Table (SPT), a large collection of bijective associations between textual phrases and their corresponding segmentations. Leveraging recent progress in object recognition and natural language semantics, we show how we can successfully build a high-quality segment-phrase table using minimal human supervision. More importantly, we demonstrate the unique value unleashed by this rich bimodal resource, for both vision as well as natural language understanding. First, we show that fine-grained textual labels facilitate contextual reasoning that helps in satisfying semantic constraints across image segments. This feature enables us to achieve state-of-the-art segmentation results on benchmark datasets. Next, we show that the association of high-quality segmentations to textual phrases aids in richer semantic understanding and reasoning of these textual phrases. Leveraging this feature, we motivate the problem of visual entailment and visual paraphrasing, and demonstrate its utility on a large dataset.

arXiv:1511.07916공식 코드 · Papers with Code

Natural Language Understanding with Distributed Representation

This is a lecture note for the course DS-GA 3001 <Natural Language Understanding with Distributed Representation> at the Center for Data Science , New York University in Fall, 2015. As the name of the course suggests, this lecture note introduces readers to a neural network based approach to natural language understanding/processing. In order to make it as self-contained as possible, I spend much time on describing basics of machine learning and neural networks, only after which how they are used for natural languages is introduced. On the language front, I almost solely focus on language modelling and machine translation, two of which I personally find most fascinating and most fundamental to natural language understanding.

arXiv:1506.01070

Do Multi-Sense Embeddings Improve Natural Language Understanding?

Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial word-similarity tasks, we don't know if they improve real natural language understanding tasks. In this paper we introduce a multi-sense embedding model based on Chinese Restaurant Processes that achieves state of the art performance on matching human word similarity judgments, and propose a pipelined architecture for incorporating multi-sense embeddings into language understanding. We then test the performance of our model on part-of-speech tagging, named entity recognition, sentiment analysis, semantic relation identification and semantic relatedness, controlling for embedding dimensionality. We find that multi-sense embeddings do improve performance on some tasks (part-of-speech tagging, semantic relation identification, semantic relatedness) but not on others (named entity recognition, various forms of sentiment analysis). We discuss how these differences may be caused by the different role of word sense information in each of the tasks. The results highlight the importance of testing embedding models in real applications.

arXiv:1511.09460

Ask, and shall you receive?: Understanding Desire Fulfillment in Natural Language Text

The ability to comprehend wishes or desires and their fulfillment is important to Natural Language Understanding. This paper introduces the task of identifying if a desire expressed by a subject in a given short piece of text was fulfilled. We propose various unstructured and structured models that capture fulfillment cues such as the subject's emotional state and actions. Our experiments with two different datasets demonstrate the importance of understanding the narrative and discourse structure to address this task.

arXiv:1506.04089공식 코드 · Papers with Code

Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences

We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents. Our alignment-based encoder-decoder model with long short-term memory recurrent neural networks (LSTM-RNN) translates natural language instructions to action sequences based upon a representation of the observable world state. We introduce a multi-level aligner that empowers our model to focus on sentence "regions" salient to the current world state by using multiple abstractions of the input sentence. In contrast to existing methods, our model uses no specialized linguistic resources (e.g., parsers) or task-specific annotations (e.g., seed lexicons). It is therefore generalizable, yet still achieves the best results reported to-date on a benchmark single-sentence dataset and competitive results for the limited-training multi-sentence setting. We analyze our model through a series of ablations that elucidate the contributions of the primary components of our model.

arXiv:1603.06677

Learning Executable Semantic Parsers for Natural Language Understanding

For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm. Semantic parsers map natural language into logical forms, the classic representation for many important linguistic phenomena. The modern twist is that we are interested in learning semantic parsers from data, which introduces a new layer of statistical and computational issues. This article lays out the components of a statistical semantic parser, highlighting the key challenges. We will see that semantic parsing is a rich fusion of the logical and the statistical world, and that this fusion will play an integral role in the future of natural language understanding systems.

arXiv:1606.05286

Spectral decomposition method of dialog state tracking via collective matrix factorization

The task of dialog management is commonly decomposed into two sequential subtasks: dialog state tracking and dialog policy learning. In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate the true dialog state from noisy observations produced by the speech recognition and the natural language understanding modules. The state tracking task is primarily meant to support a dialog policy. From a probabilistic perspective, this is achieved by maintaining a posterior distribution over hidden dialog states composed of a set of context dependent variables. Once a dialog policy is learned, it strives to select an optimal dialog act given the estimated dialog state and a defined reward function. This paper introduces a novel method of dialog state tracking based on a bilinear algebric decomposition model that provides an efficient inference schema through collective matrix factorization. We evaluate the proposed approach on the second Dialog State Tracking Challenge (DSTC-2) dataset and we show that the proposed tracker gives encouraging results compared to the state-of-the-art trackers that participated in this standard benchmark. Finally, we show that the prediction schema is computationally efficient in comparison to the previous approaches.

arXiv:1606.06361공식 코드 · Papers with Code

A Probabilistic Generative Grammar for Semantic Parsing

Domain-general semantic parsing is a long-standing goal in natural language processing, where the semantic parser is capable of robustly parsing sentences from domains outside of which it was trained. Current approaches largely rely on additional supervision from new domains in order to generalize to those domains. We present a generative model of natural language utterances and logical forms and demonstrate its application to semantic parsing. Our approach relies on domain-independent supervision to generalize to new domains. We derive and implement efficient algorithms for training, parsing, and sentence generation. The work relies on a novel application of hierarchical Dirichlet processes (HDPs) for structured prediction, which we also present in this manuscript. This manuscript is an excerpt of chapter 4 from the Ph.D. thesis of Saparov (2022), where the model plays a central role in a larger natural language understanding system. This manuscript provides a new simplified and more complete presentation of the work first introduced in Saparov, Saraswat, and Mitchell (2017). The description and proofs of correctness of the training algorithm, parsing algorithm, and sentence generation algorithm are much simplified in this new presentation. We also describe the novel application of hierarchical Dirichlet processes for structured prediction. In addition, we extend the earlier work with a new model of word morphology, which utilizes the comprehensive morphological data from Wiktionary.

arXiv:1606.05679

Two Discourse Driven Language Models for Semantics

Natural language understanding often requires deep semantic knowledge. Expanding on previous proposals, we suggest that some important aspects of semantic knowledge can be modeled as a language model if done at an appropriate level of abstraction. We develop two distinct models that capture semantic frame chains and discourse information while abstracting over the specific mentions of predicates and entities. For each model, we investigate four implementations: a "standard" N-gram language model and three discriminatively trained "neural" language models that generate embeddings for semantic frames. The quality of the semantic language models (SemLM) is evaluated both intrinsically, using perplexity and a narrative cloze test and extrinsically - we show that our SemLM helps improve performance on semantic natural language processing tasks such as co-reference resolution and discourse parsing.

arXiv:1505.08149

Modeling meaning: computational interpreting and understanding of natural language fragments

In this introductory article we present the basics of an approach to implementing computational interpreting of natural language aiming to model the meanings of words and phrases. Unlike other approaches, we attempt to define the meanings of text fragments in a composable and computer interpretable way. We discuss models and ideas for detecting different types of semantic incomprehension and choosing the interpretation that makes most sense in a given context. Knowledge representation is designed for handling context-sensitive and uncertain / imprecise knowledge, and for easy accommodation of new information. It stores quantitative information capturing the essence of the concepts, because it is crucial for working with natural language understanding and reasoning. Still, the representation is general enough to allow for new knowledge to be learned, and even generated by the system. The article concludes by discussing some reasoning-related topics: possible approaches to generation of new abstract concepts, and describing situations and concepts in words (e.g. for specifying interpretation difficulties).