Spain

This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources of evidence or facts for multi-hop reasoning becomes increasingly hard when the number of sources needed to make an inference grows. Our algorithm copes with this by decomposing the selection of facts from a corpus autoregressively, conditioning the next iteration on previously selected facts. This allows us to use a pairwise learning-to-rank loss. We validate our method on datasets of the TextGraphs 2019 and 2020 Shared Tasks for explanation regeneration. Existing work on this task either evaluates facts in isolation or artificially limits the possible chains of facts, thus limiting multi-hop inference. We demonstrate that our algorithm, when used with a pre-trained transformer model, outperforms the previous state-of-the-art in terms of precision, training time and inference efficiency.

COLING 2020

Autoregressive Reasoning over Chains of Facts with Transformers

learning-to-rank

multi-hop reasoning

question answering

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.

poster

In this work, we describe the system developed by a group of undergraduates from the Indian Institutes of Technology, for the Shared Task at TextGraphs-14 on Multi-Hop Inference Explanation Regeneration (Jansen and Ustalov, 2020). The shared task required participants to develop methods to reconstruct gold explanations for elementary science questions from the WorldTree Corpus (Xie et al., 2020). Although our research was not funded by any organization and all the models were trained on freely available tools like Google Colab which restricted our computational capabilities, we have managed to achieve noteworthy results placing ourselves in 4th place with a MAP score of 0.49021 in the evaluation leaderboard and 0.5062 MAP score on the post-evaluation-phase leaderboard using RoBERTa. We incorporated some of the methods proposed in the previous edition of Textgraphs-13 (Chia et al., 2019), which proved to be very effective, improved upon them, and built a model on top of it using powerful state-of-the-art pre-trained language models like RoBERTa (Liu et al., 2019), BART (Lewis et al., 2020), SciBERT (Beltagy et al., 2019) among others. Further optimization of our work can be done with the availability of better computational resources.

Leveraging Pre-trained Language Models for Explanation Regeneration

Explanation regeneration is the task of generating simple sentence explanations for
complex scientific phenomena related question answers. This poster describes our system submission to the Textgraphs 2020 workshop shared task which is based on multiple components: a BERT baseline ranking, an Integer Linear Program (ILP) based re-scoring, and a regression model for re-ranking the explanation facts. Our system achieved a Mean Average Precision (MAP) score of 0.36592.

Explanation Regeneration via Multi-Hop ILP Inference over Knowledge Base

Explainable question answering for science questions is a challenging task that requires multi-hop inference over a large set of fact sentences. To counter the limitations of methods that view each query-document pair in isolation, we propose the LSTM-Interleaved Transformer which incorporates cross-document interactions for improved multi-hop ranking. The LIT architecture can leverage prior ranking positions in the re-ranking setting. Our model is competitive on the current leaderboard for the TextGraphs 2020 shared task, achieving a test-set MAP of 0.5607, and would have gained third place had we submitted before the competition deadline. Our code implementation is made available at https://github.com/mdda/worldtree_corpus/tree/textgraphs_2020

: LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking

Bilingual lexicons are a vital tool for under-resourced languages and recent state-of-the-art approaches to this leverage pretrained monolingual word embeddings using supervised or semi-supervised approaches. However, these approaches require cross-lingual information such as seed dictionaries to train the model and find a linear transformation between the word embedding spaces. Especially in the case of low-resourced languages, seed dictionaries are not readily available, and as such, these methods produce extremely weak results on these languages. In this work, we focus on the Dravidian languages, namely Tamil, Telugu, Kannada, and Malayalam, which are even more challenging as they are written in unique scripts. To take advantage of orthographic information and cognates in these languages, we bring the related languages into a single script. Previous approaches have used linguistically sub-optimal measures such as the Levenshtein edit distance to detect cognates, whereby we demonstrate that the longest common sub-sequence is linguistically more sound and improves the performance of bilingual lexicon induction. We show that our approach can increase the accuracy of bilingual lexicon induction methods on these languages many times, making bilingual lexicon induction approaches feasible for such under-resourced languages.

Bilingual Lexicon Induction across Orthographically-distinct Under-Resourced Dravidian Languages

The Zaza–Gorani language family is a linguistic subgroup of the Northwestern Iranian languages for which there is no significant corpus available. Motivated to create one, in this paper we present our endeavour to collect a corpus in Zazaki and Gorani languages containing over 1.6M and 194k word tokens, respectively.

Building a Corpus for the Zaza–Gorani Language Family

This paper analyses the challenge of working with dialectal variation when semi-automatically normalising and analysing historical Basque texts. This work is part of a more general ongoing project for the construction of a morphosyntactically annotated historical corpus of Basque called Basque in the Making (BIM): A Historical Look at a European Language Isolate, whose main objective is the systematic and diachronic study of a number of grammatical features. This will
be not only the first tagged corpus of historical Basque, but also a means to improve language processing tools by analysing historical Basque varieties more or less distant from present-day standard Basque.

Dealing with dialectal variation in the construction of the Basque historical corpus

In this work, we systematically investigate different set-ups for training of neural machine translation (NMT) systems for translation into Croatian and Serbian, two closely related South Slavic languages. We explore English and German as source languages, different sizes and types of training corpora, as well as bilingual and multilingual systems. We also explore translation of English IMDb user movie reviews, a domain/genre where only monolingual data are available. 

First, our results confirm that multilingual systems with joint target languages perform better. 
Furthermore, translation performance from English is much better than from German, partly because German is morphologically more complex and partly because the corpus consists mostly of parallel human translations instead of original text and its human translation. The translation from German should be further investigated systematically.

For translating user reviews, creating synthetic in-domain parallel data through back- and forward-translation and adding them to a small out-of-domain parallel corpus can yield performance comparable with a system trained on a full out-of-domain corpus. However, it is still not clear what is the optimal size of synthetic in-domain data, especially for forward-translated data where the target language is machine translated.
More detailed research including manual evaluation and analysis is needed in this direction.

Neural Machine Translation for translating into Croatian and Serbian

In this paper, as a preliminary study of its kind, we propose an approach for the tokenization of the Sorani and Kurmanji dialects of Kurdish using a lexicon and a morphological analyzer. We demonstrate how the morphological complexity of the language along with the lack of a unified orthography can be efficiently addressed in tokenization. We also develop an annotated dataset for which our approach outperforms the performance of unsupervised methods.

A Tokenization System for the Kurdish Language

Deep neural networks have been employed for various spoken language recognition tasks, including tasks that are multilingual by definition such as spoken language identification. In this paper, we present a neural model for Slavic language identification in speech signals and analyze its emergent representations to investigate whether they reflect objective measures of language relatedness and/or non-linguists’ perception of language similarity. While our analysis shows that the language representation space indeed captures language relatedness to a great extent, we find perceptual confusability between languages in our study to be the best predictor of the language representation similarity.

Rediscovering the Slavic Continuum in Representations Emerging from Neural Models of Spoken Language Identification

Occitan is a Romance language spoken mainly in the south of France. It has no official status in the country, it is not standardized and displays important diatopic variation resulting in a rich system of dialects. Recently, we created a first treebank for this language. However, this corpus is based exclusively on texts in the Lengadocian dialect. Our paper describes the work aimed at extending the existing corpus with content in three new dialects, namely Gascon, Provençau and Lemosin. We describe both the annotation of initial content in these new varieties of Occitan and experiments allowing us to identify the most efficient method for further enrichment of the corpus. We observe that parsing models trained on Occitan dialects achieve better results than a delexicalized model trained on other Romance languages despite the latter training corpus being much larger (20K vs 900K tokens). The results of the native Occitan models show an important impact of cross-dialectal lexical variation, whereas syntactic variation seems to affect the systems less. We hope that these results, as well as the associated corpus, incorporating several Occitan varieties, will facilitate the training of robust NLP tools, capable of processing all kinds of Occitan texts.

Autoregressive Reasoning over Chains of Facts with Transformers

Downloads

Next from COLING 2020

Leveraging Pre-trained Language Models for Explanation Regeneration

Similar lecture

Autoregressive Reasoning over Chains of Facts with Transformers

Autoregressive Reasoning over Chains of Facts with Transformers

.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

Leveraging Pre-trained Language Models for Explanation Regeneration

Similar lecture

Autoregressive Reasoning over Chains of Facts with Transformers

Downloads