Thailand

We present the TAPAS contribution to theShared Task on Statement Verification and Evidence Finding with Tables (SemEval 2021Task 9, Wang et al. (2021)). SEMTABFACT Task A is a classification task of recognising if a statement is entailed, neutral or refuted by the content of a given table. We adopt the binary TAPAS model of Eisenschlos et al. (2020) to this task. We learn two binary classification models: A first model to predict if a statement is neutral or non-neutral and a second one to predict if it is entailed or refuted. As the sharedtask training set contains only entailed or refuted examples, we generate artificial neutral examples to train the first model. Both models are pre-trained using a MASKLM objective, intermediate counter-factual and synthetic data(Eisenschlos et al., 2020) and TABFACT(Chenet al., 2020), a large table entailment dataset. We find that the artificial neutral examples are somewhat effective at training the first model, achieving 68.03 test F1 versus the 60.47 of amajority baseline. For the second stage, we find that the pre-training on the intermediate data and TABFACT improves the results over MASKLM pre-training (68.03 vs 57.01)

IJCNLP-AACL 2021

TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training

sem-tab-fact

semeval-2021 task 9

tapas

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

workshop paper

Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labeling tasks due to their respective strengths. However, existing methods solely fuse lexicon features via a shallow and random initialized sequence layer and do not integrate them into the bottom layers of BERT. In this paper, we propose Lexicon Enhanced BERT (LEBERT) for Chinese sequence labeling, which integrates external lexicon knowledge into BERT layers directly by a Lexicon Adapter layer. Compared with existing methods, our model facilitates deep lexicon knowledge fusion at the lower layers of BERT. Experiments on ten Chinese datasets of three tasks including Named Entity Recognition, Word Segmentation, and Part-of-Speech Tagging, show that LEBERT achieves state-of-the-art results.

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

In recent years, math word problem solving has received considerable attention and achieved promising results, but previous methods rarely take numerical values into consideration.
Most methods treat the numerical values in the problems as number symbols, and ignore the prominent role of the numerical values in solving the problem.
In this paper, we propose a novel approach called NumS2T, which enhances math word problem solving performance by explicitly incorporating numerical values into a sequence-to-tree network.
In addition, a numerical properties prediction mechanism is used to capture the category and comparison information of numerals and measure their importance in global expressions.
Experimental results on the Math23K and APE datasets demonstrate that our model achieves better performance than existing state-of-the-art models.

Math Word Problem Solving with Explicit Numerical Values

Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions. Herein, we propose Neural-Symbolic Solver (NS-Solver) to explicitly and seamlessly incorporate different levels of symbolic constraints by auxiliary tasks. Our NS-Solver consists of a problem reader to encode problems, a programmer to generate symbolic equations, and a symbolic executor to obtain answers. Along with target expression supervision, our solver is also optimized via 4 new auxiliary objectives to enforce different symbolic reasoning: a) self-supervised number prediction task predicting both number quantity and number locations; b) commonsense constant prediction task predicting what prior knowledge (e.g. how many legs
a chicken has) is required; c) program consistency checker computing the semantic loss between predicted equation and target equation to ensure reasonable equation mapping; d) duality exploiting task exploiting the quasi-duality between symbolic equation generation and problem’s part-of-speech generation to enhance the understanding ability of a solver. Besides, to provide a more realistic and challenging benchmark for developing a universal and scalable solver, we also construct a new largescale MWP benchmark CM17K consisting of 4 kinds of MWPs (arithmetic, one-unknown linear, one-unknown non-linear, equation set) with more than 17K samples. Extensive experiments on Math23K and our CM17k demonstrate the superiority of our NS-Solver compared to state-of-the-art methods.

Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks

Recently, the performance of Pre-trained Language Models (PLMs) has been significantly improved by injecting knowledge facts to enhance their abilities of language understanding. For medical domains, the background knowledge sources are especially useful, due to the massive medical terms and their complicated relations are difficult to understand in text.
In this work, we introduce SMedBERT, a medical PLM trained on large-scale medical corpora, incorporating deep structured semantic knowledge from neighbours of linked-entity.
In SMedBERT, the mention-neighbour hybrid attention is proposed to learn heterogeneous-entity information, which infuses the semantic representations of entity types into the homogeneous neighbouring entity structure.
Apart from knowledge integration as external features, we propose to employ the neighbors of linked-entities in the knowledge graph as additional global contexts of text mentions, allowing them to communicate via shared neighbors, thus enrich their semantic representations.
Experiments demonstrate that SMedBERT significantly outperforms strong baselines in various knowledge-intensive Chinese medical tasks. It also improves the performance of other tasks such as question answering, question matching and natural language inference.

SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining

When evaluating an article and the claims it makes, a critical reader must be able to assess where the 
information presented comes from, and whether the various claims are mutually consistent and support the conclusion. This motivates the study of \emph{claim provenance}, which seeks to trace and explain the origins of claims. In this paper, we introduce new techniques to model and reason about the provenance of \emph{multiple} interacting claims, including how to capture \emph{fine-grained} information about the context. Our solution hinges on first identifying the sentences that potentially contain important external information. We then develop a query generator with our novel \emph{rank-aware cross attention} mechanism, which aims at generating metadata for the source article, based on the context and the signals collected from a search engine. This establishes relevant search queries, and it allows us to obtain source article candidates for each identified sentence and propose an ILP based algorithm to infer the best sources. We experiment with a newly created evaluation dataset, Politi-Prov, based on fact-checking articles from \url{www.politifact.com}; our experimental results show that our solution leads to a significant improvement over baselines.

What is Your Article Based On? Inferring Fine-grained Provenance

The poster describes the winning system in the End-to-end Pipeline phase for the NLPContributionGraph task. Given a paper in NLP domain, the model can automatically construct knowledge graph for this paper. The work aims to help researches read various papers and do their work more efficiently.

Boosting BERT with Sampling and Adversarial Training for Knowledge Extraction

This paper describes our system for verifying statements with tables at SemEval-2021 Task 9. We developed a two-stage verifying system based on the latest table-based pre-trained model GraPPa. Multiple networks are devised to verify different types of statements in the competition dataset and an adaptive model ensembling technique is applied to ensemble models in both stages. A statement-slot-based symbolic operation module is also used in our system to further improve the performance and stability of the system. Our model achieves second place in the 3-way classification and fourth place in the 2-way classification evaluation. Several ablation experiments show the effectiveness of different modules proposed in this paper.

THiFly_Queens at SemEval-2021 Task 9: Two-stage Statement Verification with Adaptive Ensembling and Slot-based Operation

This paper describes PTST, a source-free unsupervised domain adaptation technique for sequence tagging, and its application to the SemEval-2021 Task 10 on time expression recognition. PTST is an extension of the cross-lingual parsimonious parser transfer framework (Kurniawan et al., 2021), which uses high-probability predictions of the source model as a supervision signal in self-training. We extend the framework to a sequence prediction setting, and demonstrate its applicability to unsupervised domain adaptation. PTST achieves F1 score of 79.6% on the official test set, with the precision of 90.1%, the highest out of 14 submissions.

PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such assumptionis rarely plausible in the real-world and may causes data-privacy issues, especially when the label of the source domain can be a sensitive attribute as an identifier. In our systems, two different frameworks are designed to solve text classification and sequence labeling. These approaches are tested to be effective which ranks the third among all system in subtask A, and ranks the first among all system in subtask B.

BLCUFIGHT at SemEval-2021 Task 10: Novel Unsupervised Frameworks For Source-Free Domain Adaptation

Exploring the usefulness of pre-trained multilingual language models (i.e. mBERT, mDistil-BERT, and XLMR) in the task of word-in-context disambiguation, by comparing the models in two setups: fine-tuning and feature extraction.

TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training

Next from IJCNLP-AACL 2021

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

Similar lecture

A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES