Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTrainable Ranking Models to Evaluate the Semantic Accuracy of Data-to-Text Neural Generator
نماذج التصنيف القابلة للتدريب لتقييم الدقة الدلالية للمولدات العصبية للبيانات إلى النص
375
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذه الورقة، نقدم متري جديد يعتمد على تضمين التعاون على نماذج التصنيف القابلة للتدريب لتقييم الدقة الدلالية لمولدات البيانات النصية العصبية. هذا المتريات مناسب بشكل خاص لتقييم أداء مولد النص بشكل خاص بشكل خاص وتقييم فعليا عندما يمكن ربط الجداول بمراجع متعددة وقيم الجدول تحتوي على كلمات نصية نصية. نقدم أولا كيف يمكن للمرء تنفيذ ومزيد من التخصص المتخصص من خلال تدريب نماذج التصنيف الأساسية في مجموعة بيانات قانونية إلى نصية. نظهر كيف قد يوفر ذلك تقييما أكثر قوة من مخططات التقييم الأخرى في الإعدادات الصعبة باستخدام مجموعة بيانات تضم أي رسوم بين قيم الجدول ومراجعها. أخيرا، نقوم بتقييم قدرات تعميمها على مجموعة بيانات معروفة، و WEBNLG، بمقارنتها بالتقييم البشري ومقياس تم إدخاله مؤخرا بناء على الاستدلال اللغوي الطبيعي. بعد ذلك، توضح كيف تميز بشكل طبيعي، سواء من الناحية الكمية والنوعية والإغفالات والهلوسة.
In this paper, we introduce a new embedding-based metric relying on trainable ranking models to evaluate the semantic accuracy of neural data-to-text generators. This metric is especially well suited to semantically and factually assess the performance of a text generator when tables can be associated with multiple references and table values contain textual utterances. We first present how one can implement and further specialize the metric by training the underlying ranking models on a legal Data-to-Text dataset. We show how it may provide a more robust evaluation than other evaluation schemes in challenging settings using a dataset comprising paraphrases between the table values and their respective references. Finally, we evaluate its generalization capabilities on a well-known dataset, WebNLG, by comparing it with human evaluation and a recently introduced metric based on natural language inference. We then illustrate how it naturally characterizes, both quantitatively and qualitatively, omissions and hallucinations.
References used
https://aclanthology.org/
rate research
Read More
While powerful pre-trained language models have improved the fluency of text generation models, semantic adequacy -the ability to generate text that is semantically faithful to the input- remains an unsolved issue. In this paper, we introduce a novel
automatic evaluation metric, Entity-Based Semantic Adequacy, which can be used to assess to what extent generation models that verbalise RDF (Resource Description Framework) graphs produce text that contains mentions of the entities occurring in the RDF input. This is important as RDF subject and object entities make up 2/3 of the input. We use our metric to compare 25 models from the WebNLG Shared Tasks and we examine correlation with results from human evaluations of semantic adequacy. We show that while our metric correlates with human evaluation scores, this correlation varies with the specifics of the human evaluation setup. This suggests that in order to measure the entity-based adequacy of generated texts, an automatic metric such as the one proposed here might be more reliable, as less subjective and more focused on correct verbalisation of the input, than human evaluation measures.
QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions. Its adaptation to Data-to-Text tasks is not straightforward, as it re
quires multimodal Question Generation and Answering systems on the considered tasks, which are seldom available. To this purpose, we propose a method to build synthetic multimodal corpora enabling to train multimodal components for a data-QuestEval metric. The resulting metric is reference-less and multimodal; it obtains state-of-the-art correlations with human judgment on the WebNLG and WikiBio benchmarks. We make data-QuestEval's code and models available for reproducibility purpose, as part of the QuestEval project.
The evaluation of question answering models compares ground-truth annotations with model predictions. However, as of today, this comparison is mostly lexical-based and therefore misses out on answers that have no lexical overlap but are still semanti
cally similar, thus treating correct answers as false. This underestimation of the true performance of models hinders user acceptance in applications and complicates a fair comparison of different models. Therefore, there is a need for an evaluation metric that is based on semantics instead of pure string similarity. In this short paper, we present SAS, a cross-encoder-based metric for the estimation of semantic answer similarity, and compare it to seven existing metrics. To this end, we create an English and a German three-way annotated evaluation dataset containing pairs of answers along with human judgment of their semantic similarity, which we release along with an implementation of the SAS metric and the experiments. We find that semantic similarity metrics based on recent transformer models correlate much better with human judgment than traditional lexical similarity metrics on our two newly created datasets and one dataset from related work.
Data-to-text generation systems are trained on large datasets, such as WebNLG, Ro-toWire, E2E or DART. Beyond traditional token-overlap evaluation metrics (BLEU or METEOR), a key concern faced by recent generators is to control the factuality of the
generated text with respect to the input data specification. We report on our experience when developing an automatic factuality evaluation system for data-to-text generation that we are testing on WebNLG and E2E data. We aim to prepare gold data annotated manually to identify cases where the text communicates more information than is warranted based on the in-put data (extra) or fails to communicate data that is part of the input (missing). While analyzing reference (data, text) samples, we encountered a range of systematic uncertainties that are related to cases on implicit phenomena in text, and the nature of non-linguistic knowledge we expect to be involved when assessing factuality. We derive from our experience a set of evaluation guidelines to reach high inter-annotator agreement on such cases.
Recent text generation research has increasingly focused on open-ended domains such as story and poetry generation. Because models built for such tasks are difficult to evaluate automatically, most researchers in the space justify their modeling choi
ces by collecting crowdsourced human judgments of text quality (e.g., Likert scores of coherence or grammaticality) from Amazon Mechanical Turk (AMT). In this paper, we first conduct a survey of 45 open-ended text generation papers and find that the vast majority of them fail to report crucial details about their AMT tasks, hindering reproducibility. We then run a series of story evaluation experiments with both AMT workers and English teachers and discover that even with strict qualification filters, AMT workers (unlike teachers) fail to distinguish between model-generated text and human-generated references. We show that AMT worker judgments improve when they are shown model-generated output alongside human-generated references, which enables the workers to better calibrate their ratings. Finally, interviews with the English teachers provide deeper insights into the challenges of the evaluation process, particularly when rating model-generated text.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
