Question answering

FewshotQA: A framework for few-shot learning of question answering tasks using pre-trained text-to-text models

EMNLP 2021

2021

The task of learning from only a few examples (called a few-shot setting) is of key importance and relevance to a real-world setting. For question answering (QA), the current state-of-the-art pre-trained models typically need finetuning on tens of thousands of examples to obtain good results. Their performance degrades significantly in a few-shot setting (< 100 examples). To address this, we propose a finetuning

Conversational AI

Establishing a new standard in answer selection precision

Alessandro Moschitti

March 19, 2021

A model that uses both local and global context improves on the state of the art by 6% and 11% on two benchmark datasets.

Search and information retrieval

Solving price per unit problem around the world: Formulating fact extraction as question answering

Tarik Arici, Kushal Kumar, Hayreddin Ceker, Anoop S V K K Saladi, Ismail Tutar

KDD 2021 TrueFact Workshop on Making a Credible Web for Tomorrow

2021

Price Per Unit (PPU) is an essential information for consumers shopping on e-commerce websites when comparing products. Finding total quantity in a product is required for computing PPU, which is not always provided by the sellers. To predict total quantity, all relevant quantities given in a product’s attributes such as title, description and image need to be inferred correctly. We formulate this problem

Machine learning

WikiSum: Coherent summarization dataset for efficient human evaluation

Nachshon Cohen, Oren Kalinsky, Yftah Ziser, Alessandro Moschitti

ACL-IJCNLP 2021

2021

Recent works have made significant advances on summarization tasks, facilitated by summarization datasets. Several existing datasets have the form of coherent-paragraph summaries. However, these datasets were curated from academic documents written for experts, making the essential step of assessing the summarization output through human evaluation very demanding. To overcome these limitations, we present

Machine learning

Joint models for answer verification in question answering systems

Zeyu Zhang, Thuy Vu, Alessandro Moschitti

ACL-IJCNLP 2021

2021

This paper studies joint models for selecting correct answer sentences among the top k provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. Our work shows that a critical step to effectively exploit an answer set regards modeling the interrelated information between pair of answers. For this purpose, we build a three-way multi-classifier

Search and information retrieval

Knowledge informed semantic parsing for conversational question answering

Raghuveer Thirukovalluru, Mukund Sridhar, Dung Thai, Shruti Chanumolu, Nicholas Monath, Shankar Ananthakrishnan, Andrew McCallum

ACL-IJCNLP 2021

2021

Smart assistants are tasked to answer various questions regarding world knowledge. These questions range from retrieval of simple facts to retrieval of complex, multi-hops question followed by various operators (i.e., filter, argmax). Semantic parsing has emerged as the state-of-the-art for answering these kinds of questions by forming queries to extract information from knowledge bases (KBs). Specially

Conversational AI

Dual reader-parser on hybrid textual and tabular evidence for open domain question answering

Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang

ACL-IJCNLP 2021

2021

The current state-of-the-art generative models for open-domain question answering (ODQA) have focused on generating direct answers from unstructured textual information. However, a large amount of world’s knowledge is stored in structured databases, and need to be accessed using query languages such as SQL. Furthermore, query languages can answer questions that require complex reasoning, as well as offering

Conversational AI

One semantic parser to parse them all: Sequence to sequence multi-task learning on semantic parsing datasets

Marco Damonte, Emilio Monti

*SEM 2021

2021

Semantic parsers map natural language utterances to meaning representations. The lack of a single standard for meaning representations led to the creation of a plethora of semantic parsing datasets. To unify different datasets and train a single model for them, we investigate the use of Multi-Task Learning (MTL) architectures. We experiment with five datasets (GEOQUERY, NLMAPS, TOP, OVERNIGHT, AMR). We

Conversational AI

Answer generation for retrieval-based question answering systems

Chao-Chun Hsu, Eric Lind, Luca Soldaini, Alessandro Moschitti

ACL Findings 2021

2021

Recent advancements in transformer-based models have greatly improved the ability of Question Answering (QA) systems to provide correct answers; in particular, answer sentence selection (AS2) models, core components of retrieval-based systems, have achieved impressive results. While generally effective, these models fail to provide a satisfying answer when all retrieved candidates are of poor quality, even

Conversational AI

Generating semantically valid adversarial questions for TableQA

Yi Zhu, Yiwei Zhou, Menglin Xia

AAAI 2021 Workshop on Towards Robust, Secure and Efficient Machine Learning

2021

Adversarial attack on question answering systems over tabular data (TableQA) can help evaluate to what extent TableQA systems can understand natural language questions and reason with tables. However, generating natural language adversarial questions is difficult, because even a single character swap could lead to huge semantic difference in human perception. In this paper, we propose SAGE (Semantically

Conversational AI

Question answering

Work with us