Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understanding

• URL: http://arxiv.org/abs/2010.03903v3
• Date: Mon, 28 Mar 2022 08:11:19 GMT
• Title: Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understanding
• Authors: Dechuan Teng, Libo Qin, Wanxiang Che, Sendong Zhao, Ting Liu
• Abstract summary: We improve Chinese spoken language understanding (SLU) by injecting word information. Our model can capture useful word information and achieve state-of-the-art performance.
• Score: 65.01421041485247
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we improve Chinese spoken language understanding (SLU) by injecting word information. Previous studies on Chinese SLU do not consider the word information, failing to detect word boundaries that are beneficial for intent detection and slot filling. To address this issue, we propose a multi-level word adapter to inject word information for Chinese SLU, which consists of (1) sentence-level word adapter, which directly fuses the sentence representations of the word information and character information to perform intent detection and (2) character-level word adapter, which is applied at each character for selectively controlling weights on word information as well as character information. Experimental results on two Chinese SLU datasets show that our model can capture useful word information and achieve state-of-the-art performance.

Related papers

• Are BabyLMs Second Language Learners? [48.85680614529188]
  This paper describes a linguistically-motivated approach to the 2024 edition of the BabyLM Challenge. Rather than pursuing a first language learning (L1) paradigm, we approach the challenge from a second language (L2) learning perspective.
  arXiv  Detail & Related papers  (2024-10-28T17:52:15Z)
• VK-G2T: Vision and Context Knowledge enhanced Gloss2Text [60.57628465740138]
  Existing sign language translation methods follow a two-stage pipeline: first converting the sign language video to a gloss sequence (i.e. Sign2Gloss) and then translating the generated gloss sequence into a spoken language sentence (i.e. Gloss2Text) We propose a vision and context knowledge enhanced Gloss2Text model, named VK-G2T, which leverages the visual content of the sign language video to learn the properties of the target sentence and exploit the context knowledge to facilitate the adaptive translation of gloss words.
  arXiv  Detail & Related papers  (2023-12-15T21:09:34Z)
• X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs [55.80189506270598]
  X-PARADE is the first cross-lingual dataset of paragraph-level information divergences. Annotators label a paragraph in a target language at the span level and evaluate it with respect to a corresponding paragraph in a source language. Aligned paragraphs are sourced from Wikipedia pages in different languages.
  arXiv  Detail & Related papers  (2023-09-16T04:34:55Z)
• Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models [67.19567060894563]
  Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks. We present a new study investigating how well PLMs capture cross-lingual word sense with Contextual Word-Level Translation (C-WLT) We find that as the model size increases, PLMs encode more cross-lingual word sense knowledge and better use context to improve WLT performance.
  arXiv  Detail & Related papers  (2023-04-26T19:55:52Z)
• Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding [26.549776399115203]
  Profile-based Spoken Language Understanding (ProSLU) requires the model that not only relies on the plain text but also the supporting profile information to predict the correct intents and slots. We introduce a large-scale human-annotated Chinese dataset with over 5K utterances and their corresponding supporting profile information. Experimental results reveal that all existing text-based SLU models fail to work when the utterances are semantically ambiguous.
  arXiv  Detail & Related papers  (2021-12-22T15:22:17Z)
• LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching [29.318730227080675]
  We introduce HowNet as an external knowledge base and propose a Linguistic knowledge Enhanced graph Transformer (LET) to deal with word ambiguity. Experimental results on two Chinese datasets show that our models outperform various typical text matching approaches.
  arXiv  Detail & Related papers  (2021-02-25T04:01:51Z)
• SLK-NER: Exploiting Second-order Lexicon Knowledge for Chinese NER [8.122270502556374]
  We present new insight into second-order lexicon knowledge (SLK) of each character in the sentence to provide more lexical word information. The proposed model can exploit more discernible lexical words information with the help of global context.
  arXiv  Detail & Related papers  (2020-07-16T15:53:02Z)
• Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text [18.455836845989523]
  segmentation error propagation is a challenge for Chinese named entity recognition systems. We propose a model (UIcwsNN) that specializes in identifying entities from Chinese social media text.
  arXiv  Detail & Related papers  (2020-04-14T09:39:35Z)
• On the Importance of Word Order Information in Cross-lingual Sequence Labeling [80.65425412067464]
  Cross-lingual models that fit into the word order of the source language might fail to handle target languages. We investigate whether making models insensitive to the word order of the source language can improve the adaptation performance in target languages.
  arXiv  Detail & Related papers  (2020-01-30T03:35:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.