Papers with semantic model
Identifying Semantic Divergences in Parallel Text without Annotations (N18-1)
Copied to clipboard
| Challenge: | Parallel sentence pairs are sentences that are translations of each other and convey the same meaning in the source and target languages. |
| Approach: | They propose a model which detects meaning divergences in parallel sentence pairs . parallel sentence pair are translations of each other, therefore often assumed to convey the same meaning . |
| Outcome: | The proposed model detects divergences more accurately than models based on word alignments. |
Top-Rank-Focused Adaptive Vote Collection for the Evaluation of Domain-Specific Semantic Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Embedding-based models are increasingly needed for domain-specific evaluation datasets. |
| Approach: | They propose a protocol for the construction of a relatedness-based evaluation dataset based on adaptive pairwise comparisons and appropriate metrics to evaluate a semantic model via the aforementioned dataset. |
| Outcome: | The proposed protocol is particularly accurate in top-rank evaluation. |
AnlamVer: Semantic Model Evaluation Dataset for Turkish - Word Similarity and Relatedness (C18-1)
Copied to clipboard
| Challenge: | a dataset for semantic model evaluation for Turkish is not available for the language . a similarity and relatedness evaluation resource is needed for higher level tasks . |
| Approach: | They propose a semantic model evaluation dataset for Turkish that evaluates word similarity and word relatedness tasks while discriminating those two relations from each other. |
| Outcome: | The proposed dataset is designed to evaluate word similarity and word relatedness tasks in Turkish. |
Programming in Natural Language with fuSE: Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding (2020.acl-main)
Copied to clipboard
| Challenge: | a new approach to teach new functions from natural language is needed to make intelligent systems programmable in everyday language. |
| Approach: | They propose to use natural language to teach intelligent systems new functions . fuSE synthesizes method signatures and API calls from spoken utterances . |
| Outcome: | The proposed system synthesizes 84.6% of method signatures and 79.2% of API calls correctly on unseen dataset. |
TARIC-SLU: A Tunisian Benchmark Dataset for Spoken Language Understanding (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing SLU resources are limited in high-resource languages such as English, Mandarin and French. |
| Approach: | They propose to use a Tunisian dialect dataset to build a semantic model of the system that is continuously annotated with dialogue acts and slots. |
| Outcome: | The proposed dataset is based on train-based and ASR-based models of train-driven conversations in Tunisian dialect. |