Resolving Indirect Referring Expressions for Entity Selection

12/21/2022
by   Mohammad Javad Hosseini, et al.
0

Recent advances in language modeling have enabled new conversational systems. In particular, it is often desirable for people to make choices among specified options when using such systems. We address the problem of reference resolution, when people use natural expressions to choose between real world entities. For example, given the choice `Should we make a Simnel cake or a Pandan cake?' a natural response from a non-expert may be indirect: `let's make the green one'. Reference resolution has been little studied with natural expressions, thus robustly understanding such language has large potential for improving naturalness in dialog, recommendation, and search systems. We create AltEntities (Alternative Entities), a new public dataset of entity pairs and utterances, and develop models for the disambiguation problem. Consisting of 42K indirect referring expressions across three domains, it enables for the first time the study of how large language models can be adapted to this task. We find they achieve 82 reasonable also invites further advances.

READ FULL TEXT

page 3

page 12

page 13

page 15

page 17

research
10/07/2020

"I'd rather just go to bed": Understanding Indirect Answers

We revisit a pragmatic inference problem in dialog: understanding indire...
research
08/02/2017

Dynamic Entity Representations in Neural Language Models

Understanding a long document requires tracking how entities are introdu...
research
10/03/2021

Probing Language Models for Understanding of Temporal Expressions

We present three Natural Language Inference (NLI) challenge sets that ca...
research
03/27/2020

Neural translation and automated recognition of ICD10 medical entities from natural language

The recognition of medical entities from natural language is an ubiquito...
research
12/16/2019

Characterizing the dynamics of learning in repeated reference games

The language we use over the course of conversation changes as we establ...
research
12/28/2022

Leveraging World Knowledge in Implicit Hate Speech Detection

While much attention has been paid to identifying explicit hate speech, ...
research
03/19/2019

When redundancy is rational: A Bayesian approach to 'overinformative' referring expressions

Referring is one of the most basic and prevalent uses of language. How d...

Please sign up or login with your details

Forgot password? Click here to reset