Speedy Gonzales: A Collection of Fast Task-Specific Models for Spanish (2024.starsem-1)
Copied to clipboard
| Challenge: | Large language models (LLMs) are a common and successful approach to language and retrieval tasks. |
| Approach: | They evaluate the available large language models in Spanish and then use knowledge distillation to refine and distill them. |
| Outcome: | The proposed models are fine-tuned and distilled on knowledge distillation and are available on huggingface.co/dccuchile. |
Similar Papers
Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference (2021.starsem-1)
Copied to clipboard
| Challenge: | InferBERT is a method to enhance transformer-based inference models with relevant relational knowledge. |
| Approach: | They propose to enhance transformer-based inference models with relevant relational knowledge by injecting relevant facts at test time into the model. |
| Outcome: | The proposed method outperforms existing models on the challenge datasets while outperforming existing models. |
Scalable Performance Analysis for Vision-Language Models (2023.starsem-1)
Copied to clipboard
| Challenge: | a new method to probe vision-language models is proposed that does not require data annotation and makes use of existing datasets. |
| Approach: | They propose a method that extracts features from a vision-language benchmark and measures their correlation with the output of the target model. |
| Outcome: | The proposed method is scalable and does not require data annotation . it can be used with other models and benchmarks, and is available at https://github.com/MichiganNLP/Scalable-VLM-Probing. |
A Benchmark Suite of Japanese Natural Questions (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing studies to solve QA tasks in an integrated manner are not available in other languages because of the lack of QA datasets. |
| Approach: | They build a Japanese version of Natural Questions using natural questions from query logs of a search engine and crowdsource it using crowdsourcing. |
| Outcome: | The proposed datasets are based on natural questions from Japanese search engines and crowdsourced. |
One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets (2021.starsem-1)
Copied to clipboard
| Challenge: | Existing semantic parsing datasets lack a single standard for meaning representations . lack of a standard led to the creation of plethora of datasets requiring expert annotators . |
| Approach: | They propose to use multi-task learning to unify different datasets and train a single model for them. |
| Outcome: | The proposed architectures yield better parsing accuracies and composition generalization than single-task models. |
When Truth Matters - Addressing Pragmatic Categories in Natural Language Inference (NLI) by Large Language Models (LLMs) (2023.starsem-1)
Copied to clipboard
| Challenge: | In this paper, we examine the ability of large language models (LLMs) to accommodate different pragmatic sentence types, such as questions, commands, and sentence fragments for natural language inference (NLI). |
| Approach: | They propose to fine-tune large language models to accommodate different sentence types for natural language inference (NLI) they also explore ChatGPT's concept of entailment by using a symbolic semantic parser. |
| Outcome: | The proposed models can accommodate different sentence types without losing too much accuracy on MNLI-matched models. |
BiQuAD: Towards QA based on deeper text understanding (2021.starsem-1)
Copied to clipboard
| Challenge: | Recent question answering and machine reading benchmarks require systems to pinpoint the span of the answer to a given text. |
| Approach: | They propose a dataset that requires deeper comprehension to answer questions extractively and deductively. |
| Outcome: | The proposed dataset outperforms existing benchmarks on extractive and deductive questions. |
MASSIVE Multilingual Abstract Meaning Representation: A Dataset and Baselines for Hallucination Detection (2024.starsem-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic formalism that captures the core meaning of an utterance. |
| Approach: | They propose to use AMR to map meanings of 1,685 utterances to 50+ languages to build a dataset 20 times larger than existing resources. |
| Outcome: | The proposed dataset covers more languages, has more utterances, and has localized or translated entities for each language. |
What do Large Language Models Learn about Scripts? (2022.starsem-1)
Copied to clipboard
| Challenge: | Script Knowledge is important for language understanding but expensive to produce manually and difficult to induce from text due to reporting bias. |
| Approach: | They propose a pipeline-based script induction framework which can generate good quality ESDs for unseen scenarios. |
| Outcome: | The proposed framework produces good quality ESDs for unseen scenarios, but manual evaluation shows there is room for improvement. |
Reading Comprehension as Natural Language Inference:A Semantic Analysis (2020.starsem-1)
Copied to clipboard
Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula
| Challenge: | In recent past, Natural language Inference (NLI) has gained significant attention, but its true impact has not been well studied. |
| Approach: | They propose to transform a large RACE dataset into an NLI model and compare it to a state-of-the-art model. |
| Outcome: | The proposed model outperforms the previous model on a question-answer concatenation form and a coherent entailment form. |
Paraphrase Identification via Textual Inference (2024.starsem-1)
Copied to clipboard
| Challenge: | Paraphrase identification (PI) and natural language inference (NLI) are important tasks in natural language processing. |
| Approach: | They propose a method for paraphrase identification and natural language inference using an NLI system to solve these tasks. |
| Outcome: | The proposed method outperforms dedicated PI models on PI datasets and provides insights into limitations of current benchmarks. |