Practical Semantic Parsing for Spoken Language Understanding

Abstract

Executable semantic parsing is the task of converting natural language utterances into logical forms that can be directly used as queries to get a response. We build a transfer learning framework for executable semantic parsing. We show that the framework is effective for Question Answering (Q&A) as well as for Spoken Language Understanding (SLU). We further investigate the case where a parser on a new domain can be learned by exploiting data on other domains, either via multitask learning between the target domain and an auxiliary domain or via pre-training on the auxiliary domain and fine-tuning on the target domain. With either flavor of transfer learning, we are able to improve performance on most domains; we experiment with public data sets such as Overnight and NLmaps as well as with commercial SLU data. The experiments carried out on data sets that are different in nature show how executable semantic parsing can unify different areas of NLP such as Q&A and SLU.

Advancing Seq2seq with Joint Paraphrase Learning

“…Overnight Across 7 out of 8 domains of Overnight, the best performing model (ParaGen) outperformed baseline up to 3.2% (Publications) with 1.6% boost on average (Table 4). We also report results from Damonte et al (2019), which is an existing work on Overnight with exact match accuracy. With our implementation of Jia and Liang (2016), we achieved a baseline higher than both of the baseline and proposed methods of Damonte et al (2019).…”

“…We also report results from Damonte et al (2019), which is an existing work on Overnight with exact match accuracy. With our implementation of Jia and Liang (2016), we achieved a baseline higher than both of the baseline and proposed methods of Damonte et al (2019). Results across all 8 domains is in Table 4.…”

Introduction to neural network‐based question answering over knowledge graphs

“…In WikiSQL , for example, a copying mechanism is required to copy SQL condition values into the query (Shi et al, 2018; X. Xu et al, 2017; Zhong et al, 2017). It has also been used for semantic parsing in general (Damonte, Goel, & Chung, 2019; Jia & Liang, 2016), when the query may contain NL strings.…”

XL-AMR: Enabling Cross-Lingual AMR Parsing with Transfer Learning Techniques

“…AMR unifies, in a single structure, a rich set of information coming from different tasks, such as Named Entity Recognition (NER), Semantic Role Labeling (SRL), Word Sense Disambiguation (WSD) and coreference resolution. Such representations are actively integrated in several Natural Language Processing (NLP) applications, inter alia, information extraction (Rao et al, 2017), text summarization (Hardy and Vlachos, 2018;Liao et al, 2018), paraphrase detection (Issa et al, 2018), spoken language understanding (Damonte et al, 2019), machine translation (Song et al, 2019b) and human-robot interaction (Bonial et al, 2020). It is therefore desirable to extend AMR semantic representations across languages along the lines of cross-lingual representations for grammatical annotation (de Marneffe et al, 2014), concepts (Conia and Navigli, 2020) and semantic roles (Akbik et al, 2015;Di Fabio et al, 2019).…”