May 2025 corrections (#5125)

* Metadata for Börje F. Karlsson (closes #4041)
* Add Saptarshi Ghosh (Cincinnati) (closes #5301)

Author: mjpost

data/xml/2020.acl.xml

@@ -8622,7 +8622,7 @@
       <title>Single-/Multi-Source Cross-Lingual <fixed-case>NER</fixed-case> via Teacher-Student Learning on Unlabeled Data in Target Language</title>
       <author><first>Qianhui</first><last>Wu</last></author>
       <author><first>Zijia</first><last>Lin</last></author>
-      <author><first>Börje</first><last>Karlsson</last></author>
+      <author><first>Börje F.</first><last>Karlsson</last></author>
       <author><first>Jian-Guang</first><last>Lou</last></author>
       <author><first>Biqing</first><last>Huang</last></author>
       <pages>6505–6514</pages>

data/xml/2020.coling.xml

@@ -1176,7 +1176,7 @@
       <title>Automatic Charge Identification from Facts: A Few Sentence-Level Charge Annotations is All You Need</title>
       <author><first>Shounak</first><last>Paul</last></author>
       <author><first>Pawan</first><last>Goyal</last></author>
-      <author><first>Saptarshi</first><last>Ghosh</last></author>
+      <author id="saptarshi-ghosh"><first>Saptarshi</first><last>Ghosh</last></author>
       <pages>1011–1022</pages>
       <abstract>Automatic Charge Identification (ACI) is the task of identifying the relevant charges given the facts of a situation and the statutory laws that define these charges, and is a crucial aspect of the judicial process. Existing works focus on learning charge-side representations by modeling relationships between the charges, but not much effort has been made in improving fact-side representations. We observe that only a small fraction of sentences in the facts actually indicates the charges. We show that by using a very small subset (&lt; 3%) of fact descriptions annotated with sentence-level charges, we can achieve an improvement across a range of different ACI models, as compared to modeling just the main document-level task on a much larger dataset. Additionally, we propose a novel model that utilizes sentence-level charge labels as an auxiliary task, coupled with the main task of document-level charge identification in a multi-task learning framework. The proposed model comprehensively outperforms a large number of recent baselines for ACI. The improvement in performance is particularly noticeable for the rare charges which are known to be especially challenging to identify.</abstract>
       <url hash="cadbda1c">2020.coling-main.88</url>

data/xml/2020.socialnlp.xml

@@ -47,7 +47,7 @@
       <author><first>Sayan</first><last>Sinha</last></author>
       <author><first>Sohan</first><last>Patro</last></author>
       <author><first>Kripa</first><last>Ghosh</last></author>
-      <author><first>Saptarshi</first><last>Ghosh</last></author>
+      <author id="saptarshi-ghosh"><first>Saptarshi</first><last>Ghosh</last></author>
       <pages>15–24</pages>
       <abstract>Although a lot of research has been done on utilising Online Social Media during disasters, there exists no system for a specific task that is critical in a post-disaster scenario – identifying resource-needs and resource-availabilities in the disaster-affected region, coupled with their subsequent matching. To this end, we present NARMADA, a semi-automated platform which leverages the crowd-sourced information from social media posts for assisting post-disaster relief coordination efforts. The system employs Natural Language Processing and Information Retrieval techniques for identifying resource-needs and resource-availabilities from microblogs, extracting resources from the posts, and also matching the needs to suitable availabilities. The system is thus capable of facilitating the judicious management of resources during post-disaster relief operations.</abstract>
       <url hash="c75f139f">2020.socialnlp-1.3</url>

data/xml/2021.acl.xml

@@ -967,7 +967,7 @@
       <author><first>Weile</first><last>Chen</last></author>
       <author><first>Huiqiang</first><last>Jiang</last></author>
       <author><first>Qianhui</first><last>Wu</last></author>
-      <author><first>Börje</first><last>Karlsson</last></author>
+      <author><first>Börje F.</first><last>Karlsson</last></author>
       <author><first>Yi</first><last>Guan</last></author>
       <pages>743–753</pages>
       <abstract>Neural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. While previous works have shown that unlabeled data in a target language can be used to improve cross-lingual model performance, we propose a novel adversarial approach (AdvPicker) to better leverage such data and further improve results. We design an adversarial learning framework in which an encoder learns entity domain knowledge from labeled source-language data and better shared features are captured via adversarial training - where a discriminator selects less language-dependent target-language data via similarity to the source language. Experimental results on standard benchmark datasets well demonstrate that the proposed method benefits strongly from this data selection process and outperforms existing state-of-the-art methods; without requiring any additional external resources (e.g., gazetteers or via machine translation).</abstract>

data/xml/2022.aacl.xml

@@ -967,7 +967,7 @@
       <author><first>Rajdeep</first><last>Mukherjee</last></author>
       <author><first>Kripabandhu</first><last>Ghosh</last></author>
       <author><first>Pawan</first><last>Goyal</last></author>
-      <author><first>Saptarshi</first><last>Ghosh</last></author>
+      <author id="saptarshi-ghosh"><first>Saptarshi</first><last>Ghosh</last></author>
       <pages>1048–1064</pages>
       <abstract>Summarization of legal case judgement documents is a challenging problem in Legal NLP. However, not much analyses exist on how different families of summarization models (e.g., extractive vs. abstractive) perform when applied to legal case documents. This question is particularly important since many recent transformer-based abstractive summarization models have restrictions on the number of input tokens, and legal documents are known to be very long. Also, it is an open question on how best to evaluate legal case document summarization systems. In this paper, we carry out extensive experiments with several extractive and abstractive summarization methods (both supervised and unsupervised) over three legal summarization datasets that we have developed. Our analyses, that includes evaluation by law practitioners, lead to several interesting insights on legal summarization in specific and long document summarization in general.</abstract>
       <url hash="eb844839">2022.aacl-main.77</url>

data/xml/2022.emnlp.xml

@@ -7364,7 +7364,7 @@
       <author><first>Yiheng</first><last>Shu</last><affiliation>Nanjing University</affiliation></author>
       <author><first>Zhiwei</first><last>Yu</last><affiliation>Microsoft Research Asia</affiliation></author>
       <author><first>Yuhan</first><last>Li</last><affiliation>Nankai University</affiliation></author>
-      <author><first>Börje</first><last>Karlsson</last><affiliation>Microsoft Research Asia</affiliation></author>
+      <author><first>Börje F.</first><last>Karlsson</last><affiliation>Microsoft Research Asia</affiliation></author>
       <author><first>Tingting</first><last>Ma</last><affiliation>Harbin Institute of Technology</affiliation></author>
       <author><first>Yuzhong</first><last>Qu</last><affiliation>Nanjing University</affiliation></author>
       <author><first>Chin-Yew</first><last>Lin</last><affiliation>Microsoft Research</affiliation></author>
@@ -9889,7 +9889,7 @@
       <author><first>Shivani</first><last>Shrivastava</last><affiliation>Goldman Sachs</affiliation></author>
       <author><first>Koustuv</first><last>Dasgupta</last><affiliation>Goldman Sachs</affiliation></author>
       <author><first>Niloy</first><last>Ganguly</last><affiliation>IIT kharagpur</affiliation></author>
-      <author><first>Saptarshi</first><last>Ghosh</last><affiliation>IIT Kharagpur</affiliation></author>
+      <author id="saptarshi-ghosh"><first>Saptarshi</first><last>Ghosh</last><affiliation>IIT Kharagpur</affiliation></author>
       <author><first>Pawan</first><last>Goyal</last><affiliation>IIT Kharagpur</affiliation></author>
       <pages>10893-10906</pages>
       <abstract>Despite tremendous progress in automatic summarization, state-of-the-art methods are predominantly trained to excel in summarizing short newswire articles, or documents with strong layout biases such as scientific articles or government reports. Efficient techniques to summarize financial documents, discussing facts and figures, have largely been unexplored, majorly due to the unavailability of suitable datasets. In this work, we present ECTSum, a new dataset with transcripts of earnings calls (ECTs), hosted by publicly traded companies, as documents, and experts-written short telegram-style bullet point summaries derived from corresponding Reuters articles. ECTs are long unstructured documents without any prescribed length limit or format. We benchmark our dataset with state-of-the-art summarization methods across various metrics evaluating the content quality and factual consistency of the generated summaries. Finally, we present a simple yet effective approach, ECT-BPS, to generate a set of bullet points that precisely capture the important facts discussed in the calls.</abstract>

data/xml/2023.acl.xml

@@ -4674,7 +4674,7 @@
       <author><first>Tingting</first><last>Ma</last><affiliation>Harbin Institute of Technology</affiliation></author>
       <author><first>Qianhui</first><last>Wu</last><affiliation>Microsoft Corporation</affiliation></author>
       <author><first>Huiqiang</first><last>Jiang</last><affiliation>Microsoft Research Asia</affiliation></author>
-      <author><first>Börje</first><last>Karlsson</last><affiliation>Beijing Academy of Artificial Intelligence (BAAI)</affiliation></author>
+      <author><first>Börje F.</first><last>Karlsson</last><affiliation>Beijing Academy of Artificial Intelligence (BAAI)</affiliation></author>
       <author><first>Tiejun</first><last>Zhao</last><affiliation>Harbin Institute of Technology</affiliation></author>
       <author><first>Chin-Yew</first><last>Lin</last><affiliation>Microsoft Research</affiliation></author>
       <pages>5995-6009</pages>
@@ -5762,7 +5762,7 @@
       <author><first>Qianhui</first><last>Wu</last><affiliation>Microsoft Corporation</affiliation></author>
       <author><first>Huiqiang</first><last>Jiang</last><affiliation>Microsoft Research Asia</affiliation></author>
       <author><first>Haonan</first><last>Yin</last><affiliation>Tsinghua University</affiliation></author>
-      <author><first>Börje</first><last>Karlsson</last><affiliation>Beijing Academy of Artificial Intelligence (BAAI)</affiliation></author>
+      <author><first>Börje F.</first><last>Karlsson</last><affiliation>Beijing Academy of Artificial Intelligence (BAAI)</affiliation></author>
       <author><first>Chin-Yew</first><last>Lin</last><affiliation>Microsoft Research</affiliation></author>
       <pages>7317-7332</pages>
       <abstract>Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-distribution (ID) examples. These approaches either train a language model from scratch or fine-tune a pre-trained language model using ID examples, and then take the perplexity output by the language model as OoD scores. In this paper, we analyze the complementary characteristic of both methods and propose a multi-level knowledge distillation approach that integrates their strengths while mitigating their limitations. Specifically, we use a fine-tuned model as the teacher to teach a randomly initialized student model on the ID examples. Besides the prediction layer distillation, we present a similarity-based intermediate layer distillation method to thoroughly explore the representation space of the teacher model. In this way, the learned student can better represent the ID data manifold while gaining a stronger ability to map OoD examples outside the ID data manifold with the regularization inherited from pre-training. Besides, the student model sees only ID examples during parameter learning, further promoting more distinguishable features for OoD detection. We conduct extensive experiments over multiple benchmark datasets, i.e., CLINC150, SST, ROSTD, 20 NewsGroups, and AG News; showing that the proposed method yields new state-of-the-art performance. We also explore its application as an AIGC detector to distinguish answers generated by ChatGPT and human experts. It is observed that our model exceeds human evaluators in the pair-expert task on the Human ChatGPT Comparison Corpus.</abstract>

data/xml/2023.emnlp.xml

@@ -4517,7 +4517,7 @@
       <author><first>Debtanu</first><last>Datta</last></author>
       <author><first>Shubham</first><last>Soni</last></author>
       <author><first>Rajdeep</first><last>Mukherjee</last></author>
-      <author><first>Saptarshi</first><last>Ghosh</last></author>
+      <author id="saptarshi-ghosh"><first>Saptarshi</first><last>Ghosh</last></author>
       <pages>5291-5302</pages>
       <abstract>Automatic summarization of legal case judgments is a practically important problem that has attracted substantial research efforts in many countries. In the context of the Indian judiciary, there is an additional complexity – Indian legal case judgments are mostly written in complex English, but a significant portion of India’s population lacks command of the English language. Hence, it is crucial to summarize the legal documents in Indian languages to ensure equitable access to justice. While prior research primarily focuses on summarizing legal case judgments in their source languages, this study presents a pioneering effort toward cross-lingual summarization of English legal documents into Hindi, the most frequently spoken Indian language. We construct the first high-quality legal corpus comprising of 3,122 case judgments from prominent Indian courts in English, along with their summaries in both English and Hindi, drafted by legal practitioners. We benchmark the performance of several diverse summarization approaches on our corpus and demonstrate the need for further research in cross-lingual summarization in the legal domain.</abstract>
       <url hash="f0c82173">2023.emnlp-main.321</url>

data/xml/2023.findings.xml

@@ -8125,7 +8125,7 @@
       <author><first>Yicheng</first><last>Xu</last><affiliation>Nanyang Technological University</affiliation></author>
       <author><first>Yan</first><last>Gao</last><affiliation>Microsoft</affiliation></author>
       <author><first>Jian-Guang</first><last>Lou</last><affiliation>Microsoft</affiliation></author>
-      <author><first>Börje</first><last>Karlsson</last><affiliation>Beijing Academy of Artificial Intelligence (BAAI)</affiliation></author>
+      <author><first>Börje F.</first><last>Karlsson</last><affiliation>Beijing Academy of Artificial Intelligence (BAAI)</affiliation></author>
       <author><first>Manabu</first><last>Okumura</last><affiliation>Tokyo Institute of Technology</affiliation></author>
       <pages>6535-6549</pages>
       <abstract>Hybrid Question-Answering (HQA), which targets reasoning over tables and passages linked from table cells, has witnessed significant research in recent years. A common challenge in HQA and other passage-table QA datasets is that it is generally unrealistic to iterate over all table rows, columns, and linked passages to retrieve evidence. Such a challenge made it difficult for previous studies to show their reasoning ability in retrieving answers. To bridge this gap, we propose a novel Table-alignment-based Cell-selection and Reasoning model (TACR) for hybrid text and table QA, evaluated on the HybridQA and WikiTableQuestions datasets. In evidence retrieval, we design a table-question-alignment enhanced cell-selection method to retrieve fine-grained evidence. In answer reasoning, we incorporate a QA module that treats the row containing selected cells as context. Experimental results over the HybridQA and WikiTableQuestions (WTQ) datasets show that TACR achieves state-of-the-art results on cell selection and outperforms fine-grained evidence retrieval baselines on HybridQA, while achieving competitive performance on WTQ. We also conducted a detailed analysis to demonstrate that being able to align questions to tables in the cell-selection stage can result in important gains from experiments of over 90% table row and column selection accuracy, meanwhile also improving output explainability.</abstract>

data/xml/2023.semeval.xml

@@ -2122,7 +2122,7 @@
       <author><first>Anup</first><last>Roy</last><affiliation>IIT Kanpur</affiliation></author>
       <author><first>Shubham Kumar</first><last>Mishra</last><affiliation>Indian Institute of Technology,Kanpur</affiliation></author>
       <author><first>Arnab</first><last>Bhattacharya</last><affiliation>Dept. of Computer Science and Engineering, IIT Kanpur</affiliation></author>
-      <author><first>Saptarshi</first><last>Ghosh</last><affiliation>IIT Kharagpur</affiliation></author>
+      <author id="saptarshi-ghosh"><first>Saptarshi</first><last>Ghosh</last><affiliation>IIT Kharagpur</affiliation></author>
       <author><first>Kripabandhu</first><last>Ghosh</last><affiliation>Indian Institute of Science Education and Research- Kolkata (IISER-K)</affiliation></author>
       <pages>1293-1303</pages>
       <abstract>This paper describes our submission to the SemEval-2023 for Task 6 on LegalEval: Understanding Legal Texts. Our submission concentrated on three subtasks: Legal Named Entity Recognition (L-NER) for Task-B, Legal Judgment Prediction (LJP) for Task-C1, and Court Judgment Prediction with Explanation (CJPE) for Task-C2. We conducted various experiments on these subtasks and presented the results in detail, including data statistics and methodology. It is worth noting that legal tasks, such as those tackled in this research, have been gaining importance due to the increasing need to automate legal analysis and support. Our team obtained competitive rankings of 15th, 11th, and 1st in Task-B, Task-C1, and Task-C2, respectively, as reported on the leaderboard.</abstract>