Papers with SSD
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots (2022.findings-acl)
Copied to clipboard
| Challenge: | Sub-Slot based task-oriented dialogs provide slot values segment by segment over multiple turns. |
| Approach: | They define a task called Sub-Slot based Task-Oriented Dialog (SSTOD) they build a Chinese dialog dataset SSD for boosting research on SSTOD. |
| Outcome: | The proposed task is called Sub-Slot based Task-Oriented Dialog (SSTOD) it includes 40K dialogs and 500K utterances from Chinese names, phone numbers, ID numbers and license plate numbers . the dataset is well annotated with sub-slot values, slot values, dialog states and actions . |
A Two-Stage Framework with Self-Supervised Distillation for Cross-Domain Text Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing work on cross-domain text classification relies on domain-invariant features or task-agnostic features. |
| Approach: | They propose a two-stage framework for cross-domain text classification that leverages or reuses rich labeled data from the source domain and unlabeled data in the target domain. |
| Outcome: | The proposed framework achieves state-of-the-art on a public cross-domain text classification benchmark. |
Collecting Linguistic Resources for Assessing Children’s Pronunciation of Nordic Languages (2024.lrec-main)
Copied to clipboard
Anne Marte Haug Olstad, Anna Smolander, Sofia Strömbergsson, Sari Ylinen, Minna Lehtonen, Mikko Kurimo, Yaroslav Getman, Tamás Grósz, Xinwei Cao, Torbjørn Svendsen, Giampiero Salvi
| Challenge: | Using annotated corpora of languages is difficult for children learning a foreign language . most effort is directed to the most popular languages and adult learners . |
| Approach: | They collect annotated corpora of languages spoken by children in three Nordic countries . they hope to make the data available for future research . |
| Outcome: | The collected data will be used to develop and evaluate computer assisted pronunciation assessment systems for non-native children learning a Nordic language (L2) and for L1 children with speech sound disorder (SSD). |
From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding (2021.acl-long)
Copied to clipboard
Shan Wu, Bo Chen, Chunlei Xin, Xianpei Han, Le Sun, Weipeng Zhang, Jiansong Chen, Fan Yang, Xunliang Cai
| Challenge: | Experimental results show that Synchronous Semantic Decoding (SSD) can achieve state-of-the-art unsupervised semantic parsing performance on multiple datasets. |
| Approach: | They propose an unsupervised method which solves the semantic gap and the structure gap by leveraging paraphrasing and grammar-constrained decoding. |
| Outcome: | The proposed method can solve the semantic gap and structure gap on multiple datasets. |
Speech Sense Disambiguation: Tackling Homophone Ambiguity in End-to-End Speech Translation (2024.acl-long)
Copied to clipboard
| Challenge: | End-to-end speech translation (ST) models require simultaneous crossmodal and crosslingual transformations to be effective. |
| Approach: | They propose a homophone-aware contrastive learning approach that integrates a speech-text masking strategy to reduce ambiguity. |
| Outcome: | The proposed approach achieves SOTA results on BLEU scores on different MuST-C and CoVoST ST tasks, underlining its effectiveness in reducing speech sense ambiguity. |
Interpretable Semantic Gradients in SSD: A PCA Sweep Approach and a Case Study on AI Discourse (2026.findings-acl)
Copied to clipboard
| Challenge: | Supervised Semantic Differential (SSD) is a mixed quantitative–interpretive method that models how text meaning varies with continuous individual-difference variables . currently no systematic method exists for choosing the number of retained components, introducing avoidable researcher degrees of freedom in the analysis pipeline. |
| Approach: | They propose a PCA sweep procedure that treats dimensionality selection as a joint criterion over representation capacity, gradient interpretability, and stability across nearby values of K. |
| Outcome: | The proposed method is based on a corpus of short posts about artificial intelligence written by Prolific participants who also completed Admiration and Rivalry narcissism scales. |
GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated significant capabilities in processing and understanding text data. |
| Approach: | They propose a structure-based instruction-based method to enhance LLM performance on complex graph tasks. |
| Outcome: | The proposed framework outperforms open-source models on graph problem-solving, but the gap is narrowing. |
Speculative Safety-Aware Decoding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Speculative Safety-Aware Decoding (SSD) equips large language models with desired safety property while accelerating inference. |
| Approach: | They propose a lightweight decoding-time approach that equips large models with the desired safety property while accelerating inference. |
| Outcome: | Experimental results show that a small language model has the desired safety property while accelerating inference. |
A Syntactic and Semantic Probe into Language Evolution based on Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on language evolution have relied on manual annotated resources and rely on dependency parsing. |
| Approach: | They propose to use attention-based structural distance and semantic space distance to measure language development. |
| Outcome: | The proposed measures show that human and LLMs share common characteristics in language processing. |