Indonesia

Word sense disambiguation (WSD) is the task of determining the sense of a word in context. Translations have been used in WSD as a source of knowledge, and even as a means of delimiting word senses. In this paper, we define three theoretical properties of the relationship between senses and translations, and argue that they constitute necessary conditions for using translations as sense inventories. The key property of One Sense per Translation (OSPT) provides a foundation for a translation-based WSD method. The results of an intrinsic evaluation experiment indicate that our method achieves a precision of approximately 93% compared to manual corpus annotations. Our extrinsic evaluation experiments demonstrate WSD improvements of up to 4.6% F1-score on difficult WSD datasets.

IJCNLP-AACL 2023

One Sense per Translation

technical paper

### Welcome to IJCNLP-AACL 2023!
I am honored and happy to welcome you to IJCNLP-AACL 2023! The conference hosts both the 13th
International Joint Conference on Natural Language Processing (IJCNLP) and the 3rd Conference of
the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL). 
The joint conferences of IJCNLP and AACL have been organized by alternating leadership in the
Asia-Pacific region, in odd years by Asian Federation of Natural Language Processing (AFNLP) and
in even years by AACL. The conference is organized by AFNLP this year. 

Considering the current situation that we are not yet fully over the coronavirus pandemic, the
conference is offered in a hybrid mode, off-line in Nusa Dua, Bali, Indonesia, and on-line with the help
of Underline, during November 1-4, 2023. For those attending off-line, I hope that you will find time to
explore the exciting local area, which remains quite warm and pleasant at this time of the year. For
those attending on-line, I hope that the attendance is not much hampered, sometimes even enhanced
and comfortable, though the on-line arrangements have been made without ample time. 

Message from Jong C. Park, Korea Advanced Institute of Science and Technology (KAIST) 
IJCNLP-AACL 2023 General Chair 
###### [Conference Handbook](https://drive.google.com/file/d/1S2JSXa105xJxIkNBfhYmGH20Om6wARBx/view?usp=sharing)

In order to acces this event page, you need to register [here](http://www.ijcnlp-aacl2023.org/)

The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics

We explore zero- and few-shot generalization for fact verification (FV), which aims to generalize the FV model trained on well-resourced domains (e.g., Wikipedia) to low-resourced domains that lack human annotations. To this end, we first construct a benchmark dataset collection that contains 11 FV datasets representing 6 domains. We conduct an empirical analysis of generalization across these FV datasets, finding that current models generalize poorly. Our analysis reveals that several factors affect generalization, including dataset size, length of evidence, and the type of claims. Finally, we show that two directions of work improve generalization: 1) incorporating domain knowledge via pretraining on specialized domains, and 2) automatically generating training data via claim generation.

Investigating Zero- and Few-shot Generalization in Fact Verification

For sequence-to-sequence tasks it is challenging to combine individual system outputs. Further, there is also often a mismatch between the decoding criterion and the one used for assessment. Minimum Bayes' Risk (MBR) decoding can be used to combine system outputs in a manner that encourages better alignment with the final assessment criterion. This paper examines MBR decoding for Grammatical Error Correction (GEC) systems, where performance is usually evaluated in terms of edits and an associated F-score. Hence, we propose a novel MBR loss function directly linked to this form of criterion. Furthermore, an approach to expand the possible set of candidate sentences is described. This builds on a current max-voting combination scheme, as well as individual edit-level selection. Experiments on three popular GEC datasets and with state-of-the-art GEC systems demonstrate the efficacy of the proposed MBR approach. Additionally, the paper highlights how varying reward metrics within the MBR decoding framework can provide control over precision, recall, and the F-score in combined GEC systems.

Minimum Bayes' Risk Decoding for System Combination of Grammatical Error Correction Systems

The diversity and Zipfian frequency distribution of natural language predicates in corpora leads to sparsity in Entailment Graphs (EGs) built by Open Relation Extraction (ORE). EGs are computationally efficient and explainable models of natural language inference, but as symbolic models, they fail if a novel premise or hypothesis vertex is missing at test-time. We present theory and methodology for overcoming such sparsity in symbolic models. First, we introduce a theory of optimal smoothing of EGs by constructing transitive chains. We then demonstrate an efficient, open-domain, and unsupervised smoothing method using an off-the-shelf Language Model to find approximations of missing premise predicates. This improves recall by 25.1 and 16.3 percentage points on two difficult directional entailment datasets, while raising average precision and maintaining model explainability. Further, in a QA task we show that EG smoothing is most useful for answering questions with lesser supporting text, where missing premise predicates are more costly. Finally, controlled experiments with WordNet confirm our theory and show that hypothesis smoothing is difficult, but possible in principle.

Smoothing Entailment Graphs with Language Models

Recent advances of large pre-trained language models have motivated significant breakthroughs in various Text-to-SQL tasks. However, a number of challenges inhibit the deployment of SQL parsers in commercial applications. In this paper, we focus on two such challenges: decoding speed and multilingual input, and introduce FastRAT, a model that includes (i) a decoder-free framework to quickly generate SQL queries from natural language questions based on SQL Semantic Predictions, (ii) a cross-lingual multi-task pre-training scheme, and (iii) a method, based on distant supervision, to extend a semantic parser to new languages.

We apply FastRAT on CSpider and Spider, two challenging zero-shot semantic parsing benchmarks. Our system achieves an average of 10x decoding speedup over a set of competitive baselines based on auto- or semi-auto-regressive decoding. In the cross-lingual CSpider dataset, our approach achieves an exact query match accuracy score of 61.3, outperforming the relevant competition. In the monolingual task, it maintains competitive performance by exhibiting less than 5% accuracy drop compared to disproportionately slower solutions.

FastRAT: Fast and Efficient Cross-lingual Text-to-SQL Semantic Parsing

Bilingual Lexicon Induction (BLI), where words are translated between two languages, is an important NLP task. While noticeable progress on BLI in rich resource languages using static word embeddings has been achieved. The word translation performance can be further improved by incorporating information from contextualized word embeddings. In this paper, we introduce ProMap, a novel approach for BLI that leverages the power of prompting pretrained multilingual and multidialectal language models to address these challenges. To overcome the employment of subword tokens in these models, ProMap relies on an effective \textit{padded prompting} of language models with a seed dictionary that achieves good performance when used independently. We also demonstrate the effectiveness of ProMap in re-ranking results from other BLI methods such as with aligned static word embeddings. When evaluated on both rich-resource and low-resource languages, ProMap consistently achieves state-of-the-art results. Furthermore, ProMap enables strong performance in few-shot scenarios (even with less than 10 training examples), making it a valuable tool for low-resource language translation. Overall, we believe our method offers both exciting and promising direction for BLI in general and low-resource languages in particular. ProMap code and data are available at https://github.com/4mekki4/promap.

ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting

Lexical-semantic resources such as wordnets and multilingual dictionaries often suffer from significant coverage issues, especially in languages other than English. While improving their coverage manually is a prohibitively expensive undertaking, current approaches to the automatic creation of such resources fail to investigate the latest advances achieved in relevant fields, such as cross-lingual annotation projection. In this work, we address these shortcomings and propose LexicoMatic, a novel resource-independent approach to the automatic construction and expansion of multilingual semantic dictionaries, in which we formulate the task as an annotation projection problem. In addition, we tackle the lack of a comprehensive multilingual evaluation framework and put forward a new entirely manually-curated benchmark featuring 9 languages. We evaluate LexicoMatic with an extensive array of experiments and demonstrate the effectiveness of our approach, achieving a new state of the art across all languages under consideration. We release our novel evaluation benchmark at: https://github.com/SapienzaNLP/lexicomatic.

LexicoMatic: Automatic Creation of Multilingual Lexical-Semantic Dictionaries

While large pre-trained language models (LLMs) have shown their impressive capabilities in various NLP tasks, they are still under-explored in the misinformation domain. In this paper, we examine LLMs with in-context learning (ICL) for news claim verification, and find that only with 4-shot demonstration examples, the performance of several prompting methods can be comparable with previous supervised models. To further boost performance, we introduce a Hierarchical Step-by-Step (HiSS) prompting method which directs LLMs to separate a claim into several subclaims and then verify each of them via multiple questions-answering steps progressively.
Experiment results on two public misinformation datasets show that HiSS prompting outperforms state-of-the-art fully-supervised approach and strong few-shot ICL-enabled baselines.

Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method

Abduction has long been seen as crucial for narrative comprehension and reasoning about everyday situations. The abductive natural language inference (αNLI) task has been proposed, and this narrative text-based task aims to infer the most plausible hypothesis from the candidates given two observations. However, the inter-sentential coherence and the model consistency have not been well exploited in the previous works on this task. In this work, we propose a prompt tuning model α-PACE, which takes self-consistency and inter-sentential coherence into consideration. Besides, we propose a general self-consistent framework that considers various narrative sequences (e.g., linear narrative and reverse chronology) for guiding the pre-trained language model in understanding the narrative context of input. We conduct extensive experiments and thorough ablation studies to illustrate the necessity and effectiveness of α-PACE. The performance of our method shows significant improvement against extensive competitive baselines.

Self-Consistent Narrative Prompts on Abductive Natural Language Inference

Much of the current progress in our field seems to be driven by a small number of industry labs that have access to computing resources, data, and financial backing on a scale that would have seemed unimaginable only a few years ago (and that remain unattainable for the majority of researchers in academia or industry). However, many of the datasets that have defined novel tasks and that have catalyzed research on new problems came out of much more modest efforts by academic researchers. I will focus on the work that my own group has done on image description and on grounded instruction giving/following in Minecraft as examples of how this kind of work has helped drive scientific progress.  

How new tasks and datasets have enabled progress in NLP

Most work on large language models (LLMs) has focused on what we call "vertical" scaling: making LLMs even better for a relatively small number of high-resource languages. We address "horizontal" scaling instead: extending LLMs to a large subset of the world's languages, focusing on low-resource languages. Our Glot500-m model is trained on more than 500 languages, many of which are not covered by any other language model. But how do we know that the model has actually learned these 500 languages? Broad low-resource evaluation turns out to be a difficult problem in itself and we tried to innovate in several ways. One issue we were not able to solve is that parts of our evaluation standard cannot be distributed due to copyright restrictions. We also find that attributing good/bad performance to the so-called curse of multilinguality is naive and there is in fact also a "boon of multilinguality". We have released Glot500-m and are in the process of making our training corpus Glot500-c publicly available. 

Premium content

One Sense per Translation

Downloads

Next from IJCNLP-AACL 2023

Investigating Zero- and Few-shot Generalization in Fact Verification

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES