This paper introduces the Database Querying and Reasoning Dataset for Question Answering (DBQR-QA), aimed at addressing the gap in current question-answering (QA) research by emphasizing the essential processes of database querying and reasoning to answer questions. Specifically designed to accommodate sequential questions and multi-hop queries, DBQR-QA more accurately mirrors the dynamics of real-world information retrieval and analysis, with a particular focus on the financial reports of US companies. The dataset’s construction, the challenges encountered during its development, the performance of large language models on this dataset, and a human evaluation are thoroughly discussed to illustrate the dataset’s complexity and highlight future research directions in querying and reasoning tasks.

This paper proposes ProtoBox, a novel method to learn contextualized box embeddings. Unlike an ordinary word embedding, which represents a word as a single vector, a box embedding represents the meaning of a word as a box in a high-dimensional space: that is suitable for representing semantic relations between words. In addition, our method aims to obtain a “contextualized” box embedding, which is an abstract representation of a word in a specific context. ProtoBox is based on Prototypical Networks, which is a robust method for classification problems, especially focusing on learning the hypernym–hyponym relation between senses. ProtoBox is evaluated on three tasks: Word Sense Disambiguation (WSD), New Sense Classification (NSC), and Hypernym Identification (HI). Experimental results show that ProtoBox outperforms baselines for the HI task and is comparable for the WSD and NSC tasks.

Aspect Category Sentiment Analysis (ACSA) is one of the main subtasks of sentiment analysis, which aims at predicting polarity over a given aspect category. Recently, generative methods emerge as an efficient way to utilize a pre-trained language model for solving ACSA. However, those methods fail to model relations of target words and opinion words in a sentence including multiple aspects. To tackle this problem, this paper proposes a method to incorporate Abstract Meaning Representation (AMR), which describes semantic representation of a sentence as a directed graph, into a text generation model. Furthermore, two regularizers are designed to guide cross attention weights allocation over AMR graphs. One is the identical regularizer that constrains attention weights of aligned nodes, the other is the entropy regularizer that helps the decoder generate tokens by heavily considering only a few related nodes in the AMR graph. Experimental results on three datasets show that the proposed method outperforms state-of-the-art methods, proving the effectiveness of our model.

In product reviews, user and product aspects are useful in sentiment analysis. Nevertheless, previous studies mainly focus on modeling user and product aspects without considering the relationship between users and products. The relationship between users and products is typically helpful in estimating the bias of a user toward a product. In this paper, we, therefore, introduce the Graph Neural Network-based model with the pre-trained Language Model (GNNLM), where the relationship between users and products is incorporated. We conducted experiments on three well-known benchmarks for sentiment classification with the user and product information. The experimental results show that the relationship between users and products improves the performance of sentiment analysis. Furthermore, GNNLM achieves state-of-the-art results on yelp-2013 and yelp-2014 datasets.

Shortcut reasoning is an irrational process of inference, which degrades the robustness of an NLP model. While a number of previous work has tackled the identification of shortcut reasoning, there are still two major limitations: (i) a method for quantifying the severity of the discovered shortcut reasoning is not provided; (ii) certain types of shortcut reasoning may be missed. To address these issues, we propose a novel method for identifying shortcut reasoning. The proposed method quantifies the severity of the shortcut reasoning by leveraging out-of-distribution data and does not make any assumptions about the type of tokens triggering the shortcut reasoning. Our experiments on Natural Language Inference and Sentiment Analysis demonstrate that our framework successfully discovers known and unknown shortcut reasoning in the previous work.

This paper proposes a method to develop a machine translation (MT) system from Myanmar Sign Language (MSL) to Myanmar Written Language (MWL) and vice versa for the deaf community. Translation of MSL is a difficult task since only a small amount of a parallel corpus between MSL and MWL is available. To address the challenge for MT of the low-resource language, transfer learning is applied. An MT model is trained first for a high-resource language pair, American Sign Language (ASL) and English, then it is used as an initial model to train an MT model between MSL and MWL. The mT5 model is used as a base MT model in this transfer learning. Additionally, a self-training technique is applied to generate synthetic translation pairs of MSL and MWL from a large monolingual MWL corpus. Furthermore, since the segmentation of a sentence is required as preprocessing of MT for the Myanmar language, several segmentation schemes are empirically compared. Results of experiments show that both transfer learning and self-training can enhance the performance of the translation between MSL and MWL compared with a baseline model fine-tuned from a small MSL-MWL parallel corpus only.

While entity retrieval models continue to advance their capabilities, our understanding of their wide-ranging applications is limited, especially in domain-specific settings. We highlighted this issue by using recent general-domain entity-linking models, LUKE and GENRE, to inject external knowledge into a question-answering (QA) model for a financial QA task with a hybrid tabular-textual dataset. We found that both models improved the baseline model by 1.57% overall and 8.86% on textual data. Nonetheless, the challenge remains as they still struggle to handle tabular inputs. We subsequently conducted a comprehensive attention-weight analysis, revealing how LUKE utilizes external knowledge supplied by GENRE. The analysis also elaborates how the injection of symbolic knowledge can be helpful and what needs further improvement, paving the way for future research on this challenging QA task and advancing our understanding of how a language model incorporates external knowledge.

Typical financial documents consist of tables, texts, and numbers. Given sufficient training data, large language models (LM) can learn the tabular structures and perform numerical reasoning well in question answering (QA). However, their performances fall significantly when data and computational resources are limited. This study improves this performance drop by infusing explicit tabular structures through a graph neural network (GNN). We proposed a model developed from the baseline of a financial QA dataset named TAT-QA. The baseline model, TagOp, consists of answer span (evidence) extraction and numerical reasoning modules. As our main contributions, we introduced two components to the model: a GNN-based evidence extraction module for tables and an improved numerical reasoning module. The latter provides a solution to TagOp’s arithmetic calculation problem specific to operations requiring number ordering, such as subtraction and division, which account for a large portion of numerical reasoning. Our evaluation shows that the graph module has the advantage in low-resource settings, while the improved numerical reasoning significantly outperforms the baseline model.

The application of span detection grows fast along with the increasing need of understanding the causes and effects of events, especially in the finance domain. However, once the syntactic clues are absent in the text, the model tends to reverse the cause and effect spans. To solve this problem, we introduce graph construction techniques to inject cause-effect graph knowledge for graph embedding. The graph features combining with BERT embedding, then are used to predict the cause effect spans. The results show our proposed graph builder method outperforms the other methods w/wo external knowledge.

We report our system description for the RDFto-Text task in English on the WebNLG 2020 Challenge. Our approach consists of two parts: 1) RDF-to-Text Generation Pipeline and 2) Plan Selection. RDF-to-Text Generation Pipeline is built on the state-of-the-art pretraining model, while Plan Selection helps decide the proper plan into the pipeline.