Papers with end-to-end systems
BeLeaf: Belief Prediction as Tree Generation (2024.naacl-demo)
Copied to clipboard
| Challenge: | a novel approach to predicting source-and-target factuality is presented . our linearized tree generation task fully accounts for the factuity tree structure . |
| Approach: | They propose a linearized tree generation task which fully accounts for factuality . they then create a system which leverages the linearized representation to create visualizations . |
| Outcome: | The proposed model and representation fully account for the factuality tree structure, generating the full chain of nested sources instead of the last source only. |
BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing hybrid question answering systems use a "prompt-and-pray" paradigm . context size limitations limit ability of many transformer-based LLMs to fit into a given prompt . |
| Approach: | They propose a superset of SQLite to act as a unified dialect for orchestrating reasoning across unstructured and structured data. |
| Outcome: | The proposed framework scales to massive datasets and improves performance while using 35% fewer tokens. |
Discourse on ASR Measurement: Introducing the ARPOCA Assessment Tool (2022.acl-srw)
Copied to clipboard
| Challenge: | Automated speech recognition (ASR) models are based on a corpus of audio recordings, but are often small or nonexistent for less common languages and dialects. |
| Approach: | This research proposal will develop a semi-automatic acoustic features extraction system that integrates phonetic transcripts with pronunciation dictionaries. |
| Outcome: | The proposed system will be used to improve language recognition and model feedback in less common languages and dialects. |
A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing systems that perform content selection and surface realization are not able to provide sufficient training data for news summarization. |
| Approach: | They propose to use a cascade architecture to perform content selection and surface realization together to generate abstracts. |
| Outcome: | The proposed architecture outperforms or outranks existing systems in terms of content selection and surface realization. |
AggGen: Ordering and Aggregating while Generating (2021.acl-long)
Copied to clipboard
| Challenge: | AggGen is a data-to-text model which re-introduces two explicit sentence planning stages into neural data- to-text systems: input ordering and input aggregation. |
| Approach: | AggGen re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. |
| Outcome: | AggGen is a data-to-text model which re-introduces two explicit sentence planning stages into neural data- to-text systems: input ordering and input aggregation. |
A-TASC: Asian TED-Based Automatic Subtitling Corpus (2025.acl-long)
Copied to clipboard
| Challenge: | Existing AS corpora and primary metric SubER focus on European languages. |
| Approach: | They propose an Asian TED-based automatic subtitling corpus derived from English TED Talks and a modification of SubER to enable reliable evaluation of subtitle quality for languages without explicit word boundaries. |
| Outcome: | The proposed corpus is based on TED Talks audio segments, transcripts, and subtitles in Chinese, Japanese, Korean, and Vietnamese. |
MuST-C: a Multilingual Speech Translation Corpus (N19-1)
Copied to clipboard
| Challenge: | Current research on spoken language translation (SLT) has to confront the scarcity of sizeable and publicly available training corpora. |
| Approach: | They propose a multilingual speech translation corpus that will facilitate the training of end-to-end systems for SLT from English into 8 languages. |
| Outcome: | The proposed multilingual speech translation corpus will facilitate the training of end-to-end systems for spoken language translation from English into 8 languages. |
Training Millions of Personalized Dialogue Agents (D18-1)
Copied to clipboard
| Challenge: | Current dialogue systems fail at being engaging for users when trained end-to-end without relying on proactive reengaging scripted strategies. |
| Approach: | They propose a dataset that provides 5 million personas and 700 million person-based dialogues. |
| Outcome: | The proposed dataset provides 5 million personas and 700 million person-based dialogues. |
Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | End-to-end spoken language understanding systems model sequence labeling as a sequence prediction task causing a divergence from its well-established token-level tagging formulation. |
| Approach: | They propose to model sequence labeling as a sequence prediction task . their systems explicitly separate the added complexity of recognizing spoken mentions from the NLU task of sequence labelling . |
| Outcome: | The proposed systems outperform both cascaded and direct models on a labeling task of named entity recognition across SLU benchmarks. |
SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolution (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing attempts to integrate singleton mention detection into end-to-end coreference resolution for English have been hampered by the lack of singletont mention spans in the OntoNotes benchmark. |
| Approach: | They propose a two-step neural mention and coreference resolution system that integrates singleton mentions with OntoNotes syntax trees to achieve a near approximation of the Ontonotes dataset with all singletont mentions. |
| Outcome: | The proposed system achieves 94% recall on a sample of gold singletons. |