Related papers: Persian Abstract Meaning Representation

Related papers

The Annotation Bottleneck in Persian Text NLP: Persian as an Annotation-Scarce Language [1.066291778823737]
Persian is often described as a low-resource language in natural language processing.<n>This paper argues that Persian is more precisely described as annotation-scarce.
arXiv Detail & Related papers (2026-08-25T15:22:11Z)
IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation [88.98544786373212]
Existing sentence representations primarily encode what a sentence says, rather than how it is expressed.<n>We develop sentence representations that capture style and dialect, decoupled from semantic content.<n>We introduce IDIOLEX, a framework for training models that combines supervision from a sentence's provenance with linguistic features of a sentence's content.
arXiv Detail & Related papers (2026-04-06T14:17:24Z)
Developing a Guideline for the Labovian-Structural Analysis of Oral Narratives in Japanese [11.653694258102275]
We introduce the first systematic guidelines for Labovian narrative analysis of Japanese data.<n>Our guidelines retain all six Labovian categories and extend the framework by providing explicit rules for clause segmentation tailored to Japanese constructions.<n>Using these guidelines, annotators achieved high agreement in clause segmentation and moderate agreement in two structural classification tasks.
arXiv Detail & Related papers (2026-03-31T07:19:04Z)
TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models [10.191206917633503]
This paper presents a comprehensive evaluation framework for assessing the cultural competence of large language models (LLMs) in Persian.<n>Our framework introduces a Persian-specific short-answer evaluation that combines rule-based morphological normalization with a hybrid syntactic and semantic similarity module.
arXiv Detail & Related papers (2026-02-26T10:08:02Z)
Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation [70.43884512651668]
We formalize Genette's (1987) theory of paratexts from literary and translation studies to introduce the task of paratextual explicitation for machine translation.<n>We construct a dataset of 560 expert-aligned paratexts from four English translations of the classical Chinese short story collection Liaozhai.<n>Our findings demonstrate the potential of paratextual explicitation in advancing machine translation beyond linguistic equivalence.
arXiv Detail & Related papers (2025-09-27T16:27:36Z)
HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark [54.73504952691398]
We set out to deliver a Hebrew Machine Reading dataset as extractive Questioning.<n>The morphologically rich nature of Hebrew poses a challenge to this endeavor.<n>We devise a novel set of guidelines, a controlled crowdsourcing protocol, and revised evaluation metrics.
arXiv Detail & Related papers (2025-08-03T15:53:01Z)
PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systems [0.0]
This paper introduces Persian Speech Recognition Benchmark(PSRB), a comprehensive benchmark designed to address this gap by incorporating diverse linguistic and acoustic conditions.<n>We evaluate ten ASR systems, including state-of-the-art commercial and open-source models, to examine performance variations and inherent biases.<n>Our findings indicate that while ASR models generally perform well on standard Persian, they struggle with regional accents, children's speech, and specific linguistic challenges.
arXiv Detail & Related papers (2025-05-27T14:14:55Z)
Survey of Abstract Meaning Representation: Then, Now, Future [4.450931715128549]
AMR represents sentences as rooted, directed acyclic graphs, where nodes correspond to concepts and edges denote relationships.<n>This survey investigates AMR and its extensions, focusing on AMR capabilities.
arXiv Detail & Related papers (2025-05-06T06:45:40Z)
Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models [60.00178316095646]
Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using datasets like NLI. Recent studies leverage large language models (LLMs) to generate sentence pairs, reducing annotation dependency. We propose a method for controlling the generation direction of LLMs in the latent space. Unlike unconstrained generation, the controlled approach ensures meaningful semantic divergence. Experiments on multiple benchmarks demonstrate that our method achieves new SOTA performance with a modest cost in ranking sentence synthesis.
arXiv Detail & Related papers (2025-02-19T12:07:53Z)
Detecting Document-level Paraphrased Machine Generated Content: Mimicking Human Writing Style and Involving Discourse Features [57.34477506004105]
Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation. We introduce novel methodologies and datasets to overcome these challenges. We propose MhBART, an encoder-decoder model designed to emulate human writing style. We also propose DTransformer, a model that integrates discourse analysis through PDTB preprocessing to encode structural features.
arXiv Detail & Related papers (2024-12-17T08:47:41Z)
Evaluating Automatic Speech Recognition Systems for Korean Meteorological Experts [48.89527378273811]
This paper explores integrating Automatic Speech Recognition into natural language query systems for Korean meteorologists.<n>We address challenges in developing ASR systems for the Korean weather domain, specifically specialized vocabulary and Korean linguistic intricacies.
arXiv Detail & Related papers (2024-10-24T05:40:07Z)
Guidelines for Fine-grained Sentence-level Arabic Readability Annotation [9.261022921574318]
The Balanced Arabic Readability Evaluation Corpus (BAREC) project is designed to address the need for comprehensive Arabic language resources aligned with diverse readability levels. Inspired by the Taha/Arabi21 readability reference, BAREC aims to provide a standardized reference for assessing sentence-level Arabic text readability across 19 distinct levels. This paper focuses on our meticulous annotation guidelines, demonstrated through the analysis of 10,631 sentences/phrases (113,651 words)
arXiv Detail & Related papers (2024-10-11T09:59:46Z)
Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach [0.0]
We introduce FarsInstruct, a dataset designed to enhance the instruction following ability of large language models. FarsInstruct comprises 197 templates across 21 distinct datasets, and we intend to update it consistently, thus augmenting its applicability.
arXiv Detail & Related papers (2024-07-15T19:17:31Z)
"You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation [60.863629647985526]
We examine the successes and limitations of the GPT-3, ChatGPT, and GPT-4 models in analysis of sentence meaning structure. We find that models can reliably reproduce the basic format of AMR, and can often capture core event, argument, and modifier structure. Overall, our findings indicate that these models out-of-the-box can capture aspects of semantic structure, but there remain key limitations in their ability to support fully accurate semantic analyses or parses.
arXiv Detail & Related papers (2023-10-26T21:47:59Z)
Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability [10.710058244695128]
This paper presents a novel semantic representation, WISeR, that overcomes challenges for Abstract Meaning Representation (AMR) Despite its strengths, AMR is not easily applied to languages or domains without predefined semantic frames. We create a new corpus of 1K English dialogue sentences in both WISeR and AMR WISeR.
arXiv Detail & Related papers (2023-09-12T17:44:40Z)
Natural Language Decompositions of Implicit Content Enable Better Text Representations [52.992875653864076]
We introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a large language model to produce sets of propositions that are inferentially related to the text that has been observed. Our results suggest that modeling the meanings behind observed language, rather than the literal text alone, is a valuable direction for NLP.
arXiv Detail & Related papers (2023-05-23T23:45:20Z)
Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation [70.58243648754507]
We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR) Compared with the original textual input, AMR is a structured semantic representation that presents the core concepts and relations in a sentence explicitly and unambiguously. Experiment results show that retrofitting multilingual sentence embeddings with AMR leads to better state-of-the-art performance on both semantic similarity and transfer tasks.
arXiv Detail & Related papers (2022-10-18T11:37:36Z)
Multilingual Word Sense Disambiguation with Unified Sense Representation [55.3061179361177]
We propose building knowledge and supervised-based Multilingual Word Sense Disambiguation (MWSD) systems. We build unified sense representations for multiple languages and address the annotation scarcity problem for MWSD by transferring annotations from rich-sourced languages to poorer ones. Evaluations of SemEval-13 and SemEval-15 datasets demonstrate the effectiveness of our methodology.
arXiv Detail & Related papers (2022-10-14T01:24:03Z)
Chinese Discourse Annotation Reference Manual [9.367612782346207]
This document provides extensive guidelines and examples for Rhetorical Structure Theory (RST) annotation in Mandarin Chinese. We first introduce preprocessing steps to prepare data for RST annotation. Secondly, we discuss syntactic criteria to segment texts into Elementary Discourse Units (EDUs) Finally, we provide examples to define and distinguish discourse relations in different genres.
arXiv Detail & Related papers (2022-10-11T11:02:42Z)
How much of UCCA can be predicted from AMR? [0.0]
We use a corpus-based approach to build two graph rewriting systems, a deterministic and a non-deterministic one. We present their evaluation and a number of ambiguities that we discovered while building our rules.
arXiv Detail & Related papers (2022-07-25T13:13:34Z)
Spanish Abstract Meaning Representation: Annotation of a General Corpus [7.837003011850223]
We build on previous work proposing the annotation of AMR in Spanish, which resulted in the release of 50 Spanish AMR annotations for the fictional text "The Little Prince" Our approach to annotation makes use of Spanish rolesets from the AnCora-Net lexicon and extends English AMR with semantic features specific to Spanish.
arXiv Detail & Related papers (2022-04-15T22:26:04Z)
ViraPart: A Text Refinement Framework for ASR and NLP Tasks in Persian [0.0]
We propose a ViraPart framework that uses embedded ParsBERT in its core for text clarifications. In the end, the proposed model for ZWNJ recognition, punctuation restoration, and Persian Ezafe construction performs the averaged F1 macro scores of 96.90%, 92.13%, and 98.50%, respectively.
arXiv Detail & Related papers (2021-10-18T08:20:40Z)
Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing [88.08581016329398]
We argue that the misprediction of concepts is due to the high relevance between English tokens and AMR concepts. We introduce bilingual input, namely the translated texts as well as non-English texts, in order to enable the model to predict more accurate concepts.
arXiv Detail & Related papers (2021-06-09T05:14:54Z)
A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing [75.36126971685034]
We treat alignment and segmentation as latent variables in our model and induce them as part of end-to-end training. Our method also approaches that of a model that relies on citetLyu2018AMRPA's segmentation rules, which were hand-crafted to handle individual AMR constructions.
arXiv Detail & Related papers (2020-10-23T21:22:50Z)
Abstractive Summarization of Spoken and Written Instructions with BERT [66.14755043607776]
We present the first application of the BERTSum model to conversational language. We generate abstractive summaries of narrated instructional videos across a wide variety of topics. We envision this integrated as a feature in intelligent virtual assistants, enabling them to summarize both written and spoken instructional content upon request.
arXiv Detail & Related papers (2020-08-21T20:59:34Z)
Normalizing Compositional Structures Across Graphbanks [67.7047900945161]
We present a methodology for normalizing discrepancies between MRs at the compositional level. Our work significantly increases the match in compositional structure between MRs and improves multi-task learning.
arXiv Detail & Related papers (2020-04-29T14:35:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.