Spain

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.

COLING 2020

Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity

similarity specialization

contextualized word embeddings

knowledge injection

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

technical paper

While pre-trained word embeddings have been shown to improve the performance of downstream tasks, many questions remain regarding their reliability: Do the same pre-trained word embeddings result in the best performance with slight changes to the training data? Do the same pre-trained embeddings perform well with multiple neural network architectures? Do imputation strategies for unknown words impact reliability? In this paper, we introduce two new metrics to understand the downstream reliability of word embeddings. We find that downstream reliability of word embeddings depends on multiple factors, including, the evaluation metric, the handling of out-of-vocabulary words, and whether the embeddings are fine-tuned.

An Empirical Study of the Downstream Reliability of Pre-Trained Word Embeddings

In this paper, we address the segmentation of books of hours, Latin devotional manuscripts of the late Middle Ages, that exhibit challenging issues: a complex hierarchical entangled structure, variable content, noisy transcriptions with no sentence markers, and strong correlations between sections for which topical information is no longer sufficient to draw segmentation boundaries. We show that the main state-of-the-art segmentation methods are either inefficient or inapplicable for books of hours and propose a bottom-up greedy approach that considerably enhances the segmentation results. We stress the importance of such hierarchical segmentation of books of hours for historians to explore their overarching differences underlying conception about Church.

Hierarchical Text Segmentation for Medieval Manuscripts

In this paper, we investigate to what extent commonly used sentence vector representation spaces reflect certain kinds of regularities.
We propose a number of schemes to induce evaluation data, based on lexical analogy data as well as semantic relationships between sentences. 
We find that different models differ a lot in their ability of reflectting linguistic regularities

Sentence Analogies: Linguistic Regularities in Sentence Embeddings

We extend the Yawipa Wiktionary Parser (Wu and Yarowsky, 2020) to extract and normalize translations from etymology glosses, and morphological form-of relations, resulting in 300K unique translations and over 4 million instances of 168 annotated morphological relations. We propose a method to identify typos in translation annotations. Using the extracted morphological data, we develop multilingual neural models for predicting three types of word formation---clipping, contraction, and eye dialect---and improve upon a standard attention baseline by using copy attention.

Wiktionary Normalization of Translations and Morphological Information

Paraphrase generation aims to generate semantically consistent sentences with different syntactic realizations. Most of the recent studies rely on the typical encoder-decoder framework where the generation process is deterministic. However, in practice, the ability to generate multiple syntactically different paraphrases is important. Recent work proposed to cooperate variational inference on a target-related latent variable to introduce the diversity. But the latent variable may be contaminated by the semantic information of other unrelated sentences, and in turn, change the conveyed meaning of generated paraphrases. In this paper, we propose a semantically consistent and syntactically variational encoder-decoder framework, which uses adversarial learning to ensure the syntactic latent variable be semantic-free. Moreover, we adopt another discriminator to improve the word-level and sentence-level semantic consistency. So the proposed framework can generate multiple semantically consistent and syntactically different paraphrases. The experiments show that our model outperforms the baseline models on the metrics based on both n-gram matching and semantic similarity, and our model can generate multiple different paraphrases by assembling different syntactic variables.

A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation

Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG). We explore the tasks of one-shot learning and zero-shot domain transfer with DILOG on SimDial and MultiWoZ. Using a single representative dialog from the restaurant domain, we train DILOG on the SimDial dataset and obtain 99+% in-domain test accuracy. We also show that the trained DILOG zero-shot transfers to all other domains with 99+% accuracy, proving the suitability of DILOG to slot-filling dialogs. We further extend our study to the MultiWoZ dataset achieving 90+% inform and success metrics. We also observe that these metrics are not capturing some of the shortcomings of DILOG in terms of false positives, prompting us to measure an auxiliary Action F1 score. We show that DILOG is 100x more data efficient than state-of-the-art neural approaches on MultiWoZ while achieving similar performance metrics. We conclude with a discussion on the strengths and weaknesses of DILOG.

Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming

Sentence complexity assessment is a relatively new task in Natural Language Processing. One of its aims is to highlight in a text which sentences are more complex to support the simplification of contents for a target audience (e.g., children, cognitively impaired users, non-native speakers and low-literacy readers (Scarton and Specia, 2018)). This task is evaluated using datasets of pairs of aligned sentences including the complex and simple version of the same sentence. For Brazilian Portuguese, the task was addressed by (Leal et al., 2018), who set up the first dataset to evaluate the task in this language, reaching 87.8% of accuracy with linguistic features. The present work advances these results, using models inspired by (Gonzalez-Garduño and Søgaard, 2018), which hold the state-of-the-art for the English language, with multi-task learning and eye-tracking measures. First-Pass Duration, Total Regression Duration and Total Fixation Duration were used in two moments; first to select a subset of linguistic features and then as an auxiliary task in the multi-task and sequential learning models. The best model proposed here reaches the new state-of-the-art for Portuguese with 97.5% accuracy 1 , an increase of almost 10 points compared to the best previous results, in addition to proposing improvements in the public dataset after analysing the errors of our best model.

Using Eye-tracking Data to Predict the Readability of Brazilian Portuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches

In this paper we present a parsing model for projective dependency trees which takes advantage of the existence of complementary dependency annotations which is the case in Arabic, with the availability of CATiB and UD treebanks. Our system performs syntactic parsing according to both annotation types jointly as a sequence of arc-creating operations, and partially created trees for one annotation are also available to the other as features for the score function. This method gives error reduction of 9.9% on CATiB and 6.1% on UD compared to a strong baseline, and ablation tests show that the main contribution of this reduction is given by sharing tree representation between tasks, and not simply sharing BiLSTM layers as is often performed in NLP multitask systems.

Multitask Easy-First Dependency Parsing

After generations of exploitation, Indigenous people often respond negatively to the idea that their languages are data ready for the taking. By treating Indigenous knowledge as a commodity, speech and language technologists risk disenfranchising local knowledge authorities, reenacting the causes of language endangerment. Scholars in related fields have responded to calls for decolonisation, and we in the speech and language technology community need to follow suit, and explore what this means for our practices that involve Indigenous languages and the communities who own them. This paper reviews colonising discourses in speech and language technology, and suggests new ways of working with Indigenous communities, and seeks to open a discussion of a postcolonial approach to computational methods for supporting language vitality.

Decolonising Speech and Language Technology

Recent high scores on pronoun translation using context-aware neural machine translation have suggested that current approaches work well. ContraPro is a notable example of a contrastive challenge set for English->German pronoun translation.

The high scores achieved by transformer models may suggest that they are able to effectively model the complicated set of inferences required to carry out pronoun translation. This entails the ability to determine which entities could be referred to, identify which entity a source-language pronoun refers to (if any), and access the target-language grammatical gender for that entity.

We first show through a series of targeted adversarial attacks that in fact current approaches are not able to model all of this information well. Inserting small amounts of distracting information is enough to strongly reduce scores, which should not be the case. We then create a new template test set ContraCAT, designed to individually assess the ability to handle the specific steps necessary for successful pronoun translation. Our analyses show that current approaches to 
context-aware NMT rely on a set of surface heuristics, which break down when translations require real reasoning. We also propose an approach for augmenting the training data, with some improvements.

Downloads

Next from COLING 2020

An Empirical Study of the Downstream Reliability of Pre-Trained Word Embeddings

Similar lecture

Does Chinese BERT Encode Word Structure?

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

An Empirical Study of the Downstream Reliability of Pre-Trained Word Embeddings

Similar lecture

Does Chinese BERT Encode Word Structure?

Downloads