Challenge: Existing studies that incorporate context in SLU have focused on domains where context is limited to a few minutes.
Approach: They propose temporal representations that combine wall-clock second difference and turn order offset information to utilize both recent and distant context in a novel large-scale setup.
Outcome: The proposed model reduces 13.04% of classification errors compared to baseline . previous studies have focused on domains where context is limited to a few minutes .

Similar Papers

Temporal Generalization for Spoken Language Understanding (2022.naacl-industry)

Copied to clipboard

Challenge: Spoken Language Understanding models are usually trained offline on historical data, but must perform well on incoming user requests after deployment.
Approach: They propose different strategies for achieving good temporal generalization . they focus on temporal drift, where the distribution of utterances may change .
Outcome: The proposed model can perform well on unseen domains, e.g., upcoming data.
Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding (N19-1)

Copied to clipboard

Challenge: Existing models that use contextual information of dialogues to improve spoken language understanding (SLU) select the wrong history when the histories are similar in content.
Approach: They propose time-aware models that automatically learn the latent time-decay function of the history without a manual time- decay.
Outcome: The proposed models achieve higher F1 scores than state-of-the-art models on a benchmark dataset .
How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogues (N18-1)

Copied to clipboard

Challenge: Spoken language understanding (SLU) is an essential component in conversational systems.
Approach: They propose a universal time-decay attention mechanism that can be used to decay utterances on the sentence-level and speaker-level.
Outcome: The proposed model significantly improves the state-of-the-art model for contextual understanding performance on the benchmark Dialogue State Tracking Challenge (DSTC4) dataset.
Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to integrate knowledge bases into end-to-end task-oriented dialogue systems are limited in their ability to properly represent the entity of KB.
Approach: They propose a framework that dynamically perceives all relevant entities and dialogue history . it uses a Memory Mask to enforce the entity to focus on its relevant entities .
Outcome: The proposed framework can achieve superior performance over the state of the arts.
Exploring Contextualized Neural Language Models for Temporal Dependency Parsing (2020.emnlp-main)

Copied to clipboard

Challenge: Recent work shows that deep contextualized language models (LMs) can extract temporal relations between events and time expressions.
Approach: They propose a temporal relation extraction technique which extracts temporal relations between events and time expressions.
Outcome: The proposed method significantly improves temporal dependency parsing, the authors show . their work compares the proposed method to other methods and shows where they may fail .
Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to track dialogue state are limited due to data sparsity and long dialogues.
Approach: They propose to use the previous dialogue state and current dialogue utterance as input for DST.
Outcome: The proposed approach outperforms existing methods and improves existing ones.
How much do contextualized representations encode long-range context? (2025.findings-naacl)

Copied to clipboard

Challenge: Existing studies of contextualized representations focus on short sequences of tens to hundreds of tokens, whereas modern language models handle hundreds of thousands of token in a single context window.
Approach: They use a perturbation setup and a metric to capture contextualization of long-range patterns from the perspective of representation geometry.
Outcome: The proposed model can encode long-range contexts, but it's not fully recurrent, the authors say . their results suggest improvements in existing language models .
Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods for word embeddings have been used to model semantic relations with word embeds.
Approach: They propose a method that leverages contextual embeddings for diachronic semantic shift detection by generating time specific word representations from BERT embedds.
Outcome: The proposed method performs comparable to the current state-of-the-art without time consuming domain adaptation on large corpora.
Sharing Encoder Representations across Languages, Domains and Tasks in Large-Scale Spoken Language Understanding (2023.acl-industry)

Copied to clipboard

Challenge: Larger encoders can improve accuracy for spoken language understanding (SLU) but are difficult to use given the inference latency constraints of online systems.
Approach: They propose to use a larger 170M parameter BERT encoder that shares representations across languages, domains and tasks for SLU.
Outcome: The proposed encoders achieve state-of-the-art performance on numerous NLP tasks.
Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models (P19-1)

Copied to clipboard

Challenge: Recent studies show that document classifiers can become more stable over time when trained in ways that account for temporal variations.
Approach: They propose a method for embedding diachronic word embedds into document classification models . they propose 'time-driven neural classification model' that accounts for temporal variations .
Outcome: The proposed model can be trained on six corpora and make it more robust over time.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations