ingested acl 2022 dois (acl-org#1972)

data/xml/2022.bigscience.xml

@@ -33,6 +33,7 @@
       <bibkey>jin-etal-2022-lifelong</bibkey>
       <pwcdataset url="https://paperswithcode.com/dataset/s2orc">S2ORC</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/scierc">SciERC</pwcdataset>
+      <doi>10.18653/v1/2022.bigscience-1.1</doi>
     </paper>
     <paper id="2">
       <title>Using <fixed-case>ASR</fixed-case>-Generated Text for Spoken Language Modeling</title>
@@ -47,6 +48,7 @@
       <abstract>This papers aims at improving spoken language modeling (LM) using very large amount of automatically transcribed speech. We leverage the INA (French National Audiovisual Institute) collection and obtain 19GB of text after applying ASR on 350,000 hours of diverse TV shows. From this, spoken language models are trained either by fine-tuning an existing LM (FlauBERT) or through training a LM from scratch.The new models (FlauBERT-Oral) will be shared with the community and are evaluated not only in terms of word prediction accuracy but also for two downstream tasks : classification of TV shows and syntactic parsing of speech. Experimental results show that FlauBERT-Oral is better than its initial FlauBERT version demonstrating that, despite its inherent noisy nature, ASR-Generated text can be useful to improve spoken language modeling.</abstract>
       <url hash="db785133">2022.bigscience-1.2</url>
       <bibkey>herve-etal-2022-using</bibkey>
+      <doi>10.18653/v1/2022.bigscience-1.2</doi>
     </paper>
     <paper id="3">
       <title>You reap what you sow: On the Challenges of Bias Evaluation Under Multilingual Settings</title>
@@ -71,6 +73,7 @@
       <url hash="eb2f21e0">2022.bigscience-1.3</url>
       <bibkey>talat-etal-2022-reap</bibkey>
       <pwcdataset url="https://paperswithcode.com/dataset/crows-pairs">CrowS-Pairs</pwcdataset>
+      <doi>10.18653/v1/2022.bigscience-1.3</doi>
     </paper>
     <paper id="4">
       <title>Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model</title>
@@ -87,6 +90,7 @@
       <pwcdataset url="https://paperswithcode.com/dataset/squad">SQuAD</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/sst">SST</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/superglue">SuperGLUE</pwcdataset>
+      <doi>10.18653/v1/2022.bigscience-1.4</doi>
     </paper>
     <paper id="5">
       <title><fixed-case>UNIREX</fixed-case>: A Unified Learning Framework for Language Model Rationale Extraction</title>
@@ -107,6 +111,7 @@
       <pwcdataset url="https://paperswithcode.com/dataset/multirc">MultiRC</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/sst">SST</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/e-snli">e-SNLI</pwcdataset>
+      <doi>10.18653/v1/2022.bigscience-1.5</doi>
     </paper>
     <paper id="6">
       <title>Pipelines for Social Bias Testing of Large Language Models</title>
@@ -117,6 +122,7 @@
       <abstract>The maturity level of language models is now at a stage in which many companies rely on them to solve various tasks. However, while research has shown how biased and harmful these models are, systematic ways of integrating social bias tests into development pipelines are still lacking. This short paper suggests how to use these verification techniques in development pipelines. We take inspiration from software testing and suggest addressing social bias evaluation as software testing. We hope to open a discussion on the best methodologies to handle social bias testing in language models.</abstract>
       <url hash="07ca0619">2022.bigscience-1.6</url>
       <bibkey>nozza-etal-2022-pipelines</bibkey>
+      <doi>10.18653/v1/2022.bigscience-1.6</doi>
     </paper>
     <paper id="7">
       <title>Entities, Dates, and Languages: Zero-Shot on Historical Texts with T0</title>
@@ -131,6 +137,7 @@
       <abstract>In this work, we explore whether the recently demonstrated zero-shot abilities of the T0 model extend to Named Entity Recognition for out-of-distribution languages and time periods. Using a historical newspaper corpus in 3 languages as test-bed, we use prompts to extract possible named entities. Our results show that a naive approach for prompt-based zero-shot multilingual Named Entity Recognition is error-prone, but highlights the potential of such an approach for historical languages lacking labeled datasets. Moreover, we also find that T0-like models can be probed to predict the publication date and language of a document, which could be very relevant for the study of historical texts.</abstract>
       <url hash="72fb7cb8">2022.bigscience-1.7</url>
       <bibkey>de-toni-etal-2022-entities</bibkey>
+      <doi>10.18653/v1/2022.bigscience-1.7</doi>
     </paper>
     <paper id="8">
       <title>A Holistic Assessment of the Carbon Footprint of Noor, a Very Large <fixed-case>A</fixed-case>rabic Language Model</title>
@@ -144,6 +151,7 @@
       <url hash="857bbf5a">2022.bigscience-1.8</url>
       <bibkey>lakim-etal-2022-holistic</bibkey>
       <pwcdataset url="https://paperswithcode.com/dataset/ccnet">CCNet</pwcdataset>
+      <doi>10.18653/v1/2022.bigscience-1.8</doi>
     </paper>
     <paper id="9">
       <title><fixed-case>GPT</fixed-case>-<fixed-case>N</fixed-case>eo<fixed-case>X</fixed-case>-20<fixed-case>B</fixed-case>: An Open-Source Autoregressive Language Model</title>
@@ -179,6 +187,7 @@
       <pwcdataset url="https://paperswithcode.com/dataset/prost">PROST</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/superglue">SuperGLUE</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/the-pile">The Pile</pwcdataset>
+      <doi>10.18653/v1/2022.bigscience-1.9</doi>
     </paper>
     <paper id="10">
       <title>Dataset Debt in Biomedical Language Modeling</title>
@@ -200,6 +209,7 @@
       <bibkey>fries-etal-2022-dataset</bibkey>
       <pwcdataset url="https://paperswithcode.com/dataset/blue">BLUE</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/blurb">BLURB</pwcdataset>
+      <doi>10.18653/v1/2022.bigscience-1.10</doi>
     </paper>
     <paper id="11">
       <title>Emergent Structures and Training Dynamics in Large Language Models</title>
@@ -214,6 +224,7 @@
       <abstract>Large language models have achieved success on a number of downstream tasks, particularly in a few and zero-shot manner. As a consequence, researchers have been investigating both the kind of information these networks learn and how such information can be encoded in the parameters of the model. We survey the literature on changes in the network during training, drawing from work outside of NLP when necessary, and on learned representations of linguistic features in large language models. We note in particular the lack of sufficient research on the emergence of functional units, subsections of the network where related functions are grouped or organised, within large language models and motivate future work that grounds the study of language models in an analysis of their changing internal structure during training time.</abstract>
       <url hash="1e301fe9">2022.bigscience-1.11</url>
       <bibkey>teehan-etal-2022-emergent</bibkey>
+      <doi>10.18653/v1/2022.bigscience-1.11</doi>
     </paper>
     <paper id="12">
       <title>Foundation Models of Scientific Knowledge for Chemistry: Opportunities, Challenges and Lessons Learned</title>
@@ -245,6 +256,7 @@
       <pwcdataset url="https://paperswithcode.com/dataset/wsc">WSC</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/webtext">WebText</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/wic">WiC</pwcdataset>
+      <doi>10.18653/v1/2022.bigscience-1.12</doi>
     </paper>
   </volume>
 </collection>