In this paper, we present the first automatic lexical simplification system for the Turkish language. Recent text simplification efforts rely on manually crafted simplified corpora and comprehensive NLP tools that can analyse the target text both in word and sentence levels. Turkish is a morphologically rich agglutinative language that requires unique considerations such as the proper handling of inflectional cases. Being a low-resource language in terms of available resources and industrial-strength tools, it makes the text simplification task harder to approach. We present a new text simplification pipeline based on pretrained representation model BERT together with morphological features to generate grammatically correct and semantically appropriate word-level simplifications.
For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given sentences. By substituting complex words with simple alternatives, lexical simplification (LS) is a recognized method to reduce such lexical diversity, and therefore to improve the understandability of sentences. In this paper, we leverage LS and propose a novel approach which can effectively improve the performance of PrLMs in text classification. A rule-based simplification process is applied to a given sentence. PrLMs are encouraged to predict the real label of the given sentence with auxiliary inputs from the simplified version. Using strong PrLMs (BERT and ELECTRA) as baselines, our approach can still further improve the performance in various text classification tasks.
Lexical simplification has attracted much attention in many languages, which is the process of replacing complex words in a given sentence with simpler alternatives of equivalent meaning. Although the richness of vocabulary in Chinese makes the text very difficult to read for children and non-native speakers, there is no research work for Chinese lexical simplification (CLS) task. To circumvent difficulties in acquiring annotations, we manually create the first benchmark dataset for CLS, which can be used for evaluating the lexical simplification systems automatically. In order to acquire more thorough comparison, we present five different types of methods as baselines to generate substitute candidates for the complex word that include synonym-based approach, word embedding-based approach, pretrained language model-based approach, sememe-based approach, and a hybrid approach. Finally, we design the experimental evaluation of these baselines and discuss their advantages and disadvantages. To our best knowledge, this is the first study for CLS task.
Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning, to simplify the sentence. Recently unsupervised lexical simplification approaches only rely on the complex word itself regardless of the given sentence to generate candidate substitutions, which will inevitably produce a large number of spurious candidates. In this paper, we propose a lexical simplification framework LSBert based on pretrained representation model Bert, that is capable of (1) making use of the wider context when both detecting the words in need of simplification and generating substitue candidates, and (2) taking five high-quality features into account for ranking candidates, including Bert prediction order, Bert-based language model, and the paraphrase database PPDB, in addition to the word frequency and word similarity commonly used in other LS methods. We show that our system outputs lexical simplifications that are grammatically correct and semantically appropriate, and obtains obvious improvement compared with these baselines, outperforming the state-of-the-art by 29.8 Accuracy points on three well-known benchmarks.
Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the distributional knowledge available in raw text corpora, incorporated through language modeling objectives. In this work, we complement such distributional knowledge with external lexical knowledge, that is, we integrate the discrete knowledge on word-level semantic similarity into pretraining. To this end, we generalize the standard BERT model to a multi-task learning setting where we couple BERT's masked language modeling and next sentence prediction objectives with an auxiliary task of binary word relation classification. Our experiments suggest that our "Lexically Informed" BERT (LIBERT), specialized for the word-level semantic similarity, yields better performance than the lexically blind "vanilla" BERT on several language understanding tasks. Concretely, LIBERT outperforms BERT in 9 out of 10 tasks of the GLUE benchmark and is on a par with BERT in the remaining one. Moreover, we show consistent gains on 3 benchmarks for lexical simplification, a task where knowledge about word-level semantic similarity is paramount.
Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we will show, hyperparameter choices have significant impact on the final results. We present a replication study of BERT pretraining (Devlin et al., 2019) that carefully measures the impact of many key hyperparameters and training data size. We find that BERT was significantly undertrained, and can match or exceed the performance of every model published after it. Our best model achieves state-of-the-art results on GLUE, RACE and SQuAD. These results highlight the importance of previously overlooked design choices, and raise questions about the source of recently reported improvements. We release our models and code.
Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning. Recently unsupervised lexical simplification approaches only rely on the complex word itself regardless of the given sentence to generate candidate substitutions, which will inevitably produce a large number of spurious candidates. We present a simple LS approach that makes use of the Bidirectional Encoder Representations from Transformers (BERT) which can consider both the given sentence and the complex word during generating candidate substitutions for the complex word. Specifically, we mask the complex word of the original sentence for feeding into the BERT to predict the masked token. The predicted results will be used as candidate substitutions. Despite being entirely unsupervised, experimental results show that our approach obtains obvious improvement compared with these baselines leveraging linguistic databases and parallel corpus, outperforming the state-of-the-art by more than 12 Accuracy points on three well-known benchmarks.
Current lexical simplification approaches rely heavily on heuristics and corpus level features that do not always align with human judgment. We create a human-rated word-complexity lexicon of 15,000 English words and propose a novel neural readability ranking model with a Gaussian-based feature vectorization layer that utilizes these human ratings to measure the complexity of any given word or phrase. Our model performs better than the state-of-the-art systems for different lexical simplification tasks and evaluation datasets. Additionally, we also produce SimplePPDB++, a lexical resource of over 10 million simplifying paraphrase rules, by applying our model to the Paraphrase Database (PPDB).
Text simplification (TS) can be viewed as monolingual translation task, translating between text variations within a single language. Recent neural TS models draw on insights from neural machine translation to learn lexical simplification and content reduction using encoder-decoder model. But different from neural machine translation, we cannot obtain enough ordinary and simplified sentence pairs for TS, which are expensive and time-consuming to build. Target-side simplified sentences plays an important role in boosting fluency for statistical TS, and we investigate the use of simplified sentences to train, with no changes to the network architecture. We propose to pair simple training sentence with a synthetic ordinary sentence via back-translation, and treating this synthetic data as additional training data. We train encoder-decoder model using synthetic sentence pairs and original sentence pairs, which can obtain substantial improvements on the available WikiLarge data and WikiSmall data compared with the state-of-the-art methods.
Semantic specialization is the process of fine-tuning pre-trained distributional word vectors using external lexical knowledge (e.g., WordNet) to accentuate a particular semantic relation in the specialized vector space. While post-processing specialization methods are applicable to arbitrary distributional vectors, they are limited to updating only the vectors of words occurring in external lexicons (i.e., seen words), leaving the vectors of all other words unchanged. We propose a novel approach to specializing the full distributional vocabulary. Our adversarial post-specialization method propagates the external lexical knowledge to the full distributional space. We exploit words seen in the resources as training examples for learning a global specialization function. This function is learned by combining a standard L2-distance loss with an adversarial loss: the adversarial component produces more realistic output vectors. We show the effectiveness and robustness of the proposed method across three languages and on three tasks: word similarity, dialog state tracking, and lexical simplification. We report consistent improvements over distributional word vectors and vectors specialized by other state-of-the-art specialization frameworks. Finally, we also propose a cross-lingual transfer method for zero-shot specialization which successfully specializes a full target distributional space without any lexical knowledge in the target language and without any bilingual data.
We extend sequence-to-sequence models with the possibility to control the characteristics or style of the generated output, via attention that is generated a priori (before decoding) from a latent code vector. After training an initial attention-based sequence-to-sequence model, we use a variational auto-encoder conditioned on representations of input sequences and a latent code vector space to generate attention matrices. By sampling the code vector from specific regions of this latent space during decoding and imposing prior attention generated from it in the seq2seq model, output can be steered towards having certain attributes. This is demonstrated for the task of sentence simplification, where the latent code vector allows control over output length and lexical simplification, and enables fine-tuning to optimize for different evaluation metrics.
Word sense disambiguation (WSD) improves many Natural Language Processing (NLP) applications such as Information Retrieval, Machine Translation or Lexical Simplification. WSD is the ability of determining a word sense among different ones within a polysemic lexical unit taking into account the context. The most straightforward approach uses a semantic proximity measure between the word sense candidates of the target word and those of its context. Such a method very easily entails a combinatorial explosion. In this paper, we propose two methods based on distributional analysis which enable to reduce the exponential complexity without losing the coherence. We present a comparison between the selection of distributional neighbors and the linearly nearest neighbors. The figures obtained show that selecting distributional neighbors leads to better results.
Word sense disambiguation improves many Natural Language Processing (NLP) applications such as Information Retrieval, Information Extraction, Machine Translation, or Lexical Simplification. Roughly speaking, the aim is to choose for each word in a text its best sense. One of the most popular method estimates local semantic similarity relatedness between two word senses and then extends it to all words from text. The most direct method computes a rough score for every pair of word senses and chooses the lexical chain that has the best score (we can imagine the exponential complexity that returns this comprehensive approach). In this paper, we propose to use a combinatorial optimization metaheuristic for choosing the nearest neighbors obtained by distributional selection around the word to disambiguate. The test and the evaluation of our method concern a corpus written in French by means of the semantic network BabelNet. The obtained accuracy rate is 78 % on all names and verbs chosen for the evaluation.