PyTorchKR Papers

최신 논문

총 67편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2108.03578

Language Model Evaluation in Open-ended Text Generation

Although current state-of-the-art language models have achieved impressive results in numerous natural language processing tasks, still they could not solve the problem of producing repetitive, dull and sometimes inconsistent text in open-ended text generation. Studies often attribute this problem to the maximum likelihood training objective, and propose alternative approaches by using stochastic decoding methods or altering the training objective. However, there is still a lack of consistent evaluation metrics to directly compare the efficacy of these solutions. In this work, we study different evaluation metrics that have been proposed to evaluate quality, diversity and consistency of machine-generated text. From there, we propose a practical pipeline to evaluate language models in open-ended generation task, and research on how to improve the model's performance in all dimensions by leveraging different auxiliary training objectives.

arXiv:2106.00085

Language Model Evaluation Beyond Perplexity

We propose an alternate approach to quantifying how well language models learn natural language: we ask how well they match the statistical tendencies of natural language. To answer this question, we analyze whether text generated from language models exhibits the statistical tendencies present in the human-generated text on which they were trained. We provide a framework--paired with significance tests--for evaluating the fit of language models to these trends. We find that neural language models appear to learn only a subset of the tendencies considered, but align much more closely with empirical trends than proposed theoretical distributions (when present). Further, the fit to different distributions is highly-dependent on both model architecture and generation strategy. As concrete examples, text generated under the nucleus sampling scheme adheres more closely to the type--token relationship of natural language than text produced using standard ancestral sampling; text from LSTMs reflects the natural language distributions over length, stopwords, and symbols surprisingly well.

arXiv:2102.12828공식 코드 · Papers with Code

ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning

This paper presents our systems for the three Subtasks of SemEval Task4: Reading Comprehension of Abstract Meaning (ReCAM). We explain the algorithms used to learn our models and the process of tuning the algorithms and selecting the best model. Inspired by the similarity of the ReCAM task and the language pre-training, we propose a simple yet effective technology, namely, negative augmentation with language model. Evaluation results demonstrate the effectiveness of our proposed approach. Our models achieve the 4th rank on both official test sets of Subtask 1 and Subtask 2 with an accuracy of 87.9% and an accuracy of 92.8%, respectively. We further conduct comprehensive model analysis and observe interesting error cases, which may promote future researches.

arXiv:2102.01951공식 코드 · Papers with Code

Mind the Gap: Assessing Temporal Generalization in Neural Language Models

Our world is open-ended, non-stationary, and constantly evolving; thus what we talk about and how we talk about it change over time. This inherent dynamic nature of language contrasts with the current static language modelling paradigm, which trains and evaluates models on utterances from overlapping time periods. Despite impressive recent progress, we demonstrate that Transformer-XL language models perform worse in the realistic setup of predicting future utterances from beyond their training period, and that model performance becomes increasingly worse with time. We find that, while increasing model size alone -- a key driver behind recent progress -- does not solve this problem, having models that continually update their knowledge with new information can indeed mitigate this performance degradation over time. Hence, given the compilation of ever-larger language modelling datasets, combined with the growing list of language-model-based NLP applications that require up-to-date factual knowledge about the world, we argue that now is the right time to rethink the static way in which we currently train and evaluate our language models, and develop adaptive language models that can remain up-to-date with respect to our ever-changing and non-stationary world. We publicly release our dynamic, streaming language modelling benchmarks for WMT and arXiv to facilitate language model evaluation that takes temporal dynamics into account.

arXiv:2101.11131

CLiMP: A Benchmark for Chinese Language Model Evaluation

Linguistically informed analyses of language models (LMs) contribute to the understanding and improvement of these models. Here, we introduce the corpus of Chinese linguistic minimal pairs (CLiMP), which can be used to investigate what knowledge Chinese LMs acquire. CLiMP consists of sets of 1,000 minimal pairs (MPs) for 16 syntactic contrasts in Mandarin, covering 9 major Mandarin linguistic phenomena. The MPs are semi-automatically generated, and human agreement with the labels in CLiMP is 95.8%. We evaluated 11 different LMs on CLiMP, covering n-grams, LSTMs, and Chinese BERT. We find that classifier-noun agreement and verb complement selection are the phenomena that models generally perform best at. However, models struggle the most with the ba construction, binding, and filler-gap dependencies. Overall, Chinese BERT achieves an 81.8% average accuracy, while the performances of LSTMs and 5-grams are only moderately above chance level.

arXiv:1807.06978

Improving Explainable Recommendations with Synthetic Reviews

An important task for a recommender system to provide interpretable explanations for the user. This is important for the credibility of the system. Current interpretable recommender systems tend to focus on certain features known to be important to the user and offer their explanations in a structured form. It is well known that user generated reviews and feedback from reviewers have strong leverage over the users' decisions. On the other hand, recent text generation works have been shown to generate text of similar quality to human written text, and we aim to show that generated text can be successfully used to explain recommendations. In this paper, we propose a framework consisting of popular review-oriented generation models aiming to create personalised explanations for recommendations. The interpretations are generated at both character and word levels. We build a dataset containing reviewers' feedback from the Amazon books review dataset. Our cross-domain experiments are designed to bridge from natural language processing to the recommender system domain. Besides language model evaluation methods, we employ DeepCoNN, a novel review-oriented recommender system using a deep neural network, to evaluate the recommendation performance of generated reviews by root mean square error (RMSE). We demonstrate that the synthetic personalised reviews have better recommendation performance than human written reviews. To our knowledge, this presents the first machine-generated natural language explanations for rating prediction.

arXiv:1601.00248

Contrastive Entropy: A new evaluation metric for unnormalized language models

Perplexity (per word) is the most widely used metric for evaluating language models. Despite this, there has been no dearth of criticism for this metric. Most of these criticisms center around lack of correlation with extrinsic metrics like word error rate (WER), dependence upon shared vocabulary for model comparison and unsuitability for unnormalized language model evaluation. In this paper, we address the last problem and propose a new discriminative entropy based intrinsic metric that works for both traditional word level models and unnormalized language models like sentence level models. We also propose a discriminatively trained sentence level interpretation of recurrent neural network based language model (RNN) as an example of unnormalized sentence level model. We demonstrate that for word level models, contrastive entropy shows a strong correlation with perplexity. We also observe that when trained at lower distortion levels, sentence level RNN considerably outperforms traditional RNNs on this new metric.