Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFOMO: Topics versus documents in legal eDiscovery
200
0
0.0
(
0
)
Added by
Herbert Roitblat
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Authors
Herbert Roitblat
Ask ChatGPT about the research
No Arabic abstract
In the United States, the parties to a lawsuit are required to search through their electronically stored information to find documents that are relevant to the specific case and produce them to their opposing party. Negotiations over the scope of these searches often reflect a fear that something will be missed (Fear of Missing Out: FOMO). A Recall level of 80%, for example, means that 20% of the relevant documents will be left unproduced. This paper makes the argument that eDiscovery is the process of identifying responsive information, not identifying documents. Documents are the carriers of the information; they are not the direct targets of the process. A given document may contain one or more topics or factoids and a factoid may appear in more than one document. The coupon collectors problem, Heaps law, and other analyses provide ways to model the problem of finding information from among documents. In eDiscovery, however, the parties do not know how many factoids there might be in a collection or their probabilities. This paper describes a simple model that estimates the confidence that a fact will be omitted from the produced set (the identified set), while being contained in the missed set. Two data sets are then analyzed, a small set involving microaggressions and larger set involving classification of web pages. Both show that it is possible to discover at least one example of each available topic within a relatively small number of documents, meaning the further effort will not return additional novel information. The smaller data set is also used to investigate whether the non-random order of searching for responsive documents commonly used in eDiscovery (called continuous active learning) affects the distribution of topics-it does not.
rate research
Read More
In legal eDiscovery, the parties are required to search through their electronically stored information to find documents that are relevant to a specific case. Negotiations over the scope of these searches are often based on a fear that something will be missed. This paper continues an argument that discovery should be based on identifying the facts of a case. If a search process is less than complete (if it has Recall less than 100%), it may still be complete in presenting all of the relevant available topics. In this study, Latent Dirichlet Allocation was used to identify 100 topics from all of the known relevant documents. The documents were then categorized to about 80% Recall (i.e., 80% of the relevant documents were found by the categorizer, designated the hit set and 20% were missed, designated the missed set). Despite the fact that less than all of the relevant documents were identified by the categorizer, the documents that were identified contained all of the topics derived from the full set of documents. This same pattern held whether the categorizer was a naive Bayes categorizer trained on a random selection of documents or a Support Vector Machine trained with Continuous Active Learning (which focuses evaluation on the most-likely-to-be-relevant documents). No topics were identified in either categorizers missed set that were not already seen in the hit set. Not only is a computer-assisted search process reasonable (as required by the Federal Rules of Civil Procedure), it is also complete when measured by topics.
Topic models provide a useful tool to organize and understand the structure of large corpora of text documents, in particular, to discover hidden thematic structure. Clustering documents from big unstructured corpora into topics is an important task in various areas, such as image analysis, e-commerce, social networks, population genetics. A common approach to topic modeling is to associate each topic with a probability distribution on the dictionary of words and to consider each document as a mixture of topics. Since the number of topics is typically substantially smaller than the size of the corpus and of the dictionary, the methods of topic modeling can lead to a dramatic dimension reduction. In this paper, we study the problem of estimating topics distribution for each document in the given corpus, that is, we focus on the clustering aspect of the problem. We introduce an algorithm that we call Successive Projection Overlapping Clustering (SPOC) inspired by the Successive Projection Algorithm for separable matrix factorization. This algorithm is simple to implement and computationally fast. We establish theoretical guarantees on the performance of the SPOC algorithm, in particular, near matching minimax upper and lower bounds on its estimation risk. We also propose a new method that estimates the number of topics. We complement our theoretical results with a numerical study on synthetic and semi-synthetic data to analyze the performance of this new algorithm in practice. One of the conclusions is that the error of the algorithm grows at most logarithmically with the size of the dictionary, in contrast to what one observes for Latent Dirichlet Allocation.
The organization and evolution of science has recently become itself an object of scientific quantitative investigation, thanks to the wealth of information that can be extracted from scientific documents, such as citations between papers and co-authorship between researchers. However, only few studies have focused on the concepts that characterize full documents and that can be extracted and analyzed, revealing the deeper organization of scientific knowledge. Unfortunately, several concepts can be so common across documents that they hinder the emergence of the underlying topical structure of the document corpus, because they give rise to a large amount of spurious and trivial relations among documents. To identify and remove common concepts, we introduce a method to gauge their relevance according to an objective information-theoretic measure related to the statistics of their occurrence across the document corpus. After progressively removing concepts that, according to this metric, can be considered as generic, we find that the topic organization displays a correspondingly more refined structure.
The California Innocence Project (CIP), a clinical law school program aiming to free wrongfully convicted prisoners, evaluates thousands of mails containing new requests for assistance and corresponding case files. Processing and interpreting this large amount of information presents a significant challenge for CIP officials, which can be successfully aided by topic modeling techniques.In this paper, we apply Non-negative Matrix Factorization (NMF) method and implement various offshoots of it to the important and previously unstudied data set compiled by CIP. We identify underlying topics of existing case files and classify request files by crime type and case status (decision type). The results uncover the semantic structure of current case files and can provide CIP officials with a general understanding of newly received case files before further examinations. We also provide an exposition of popular variants of NMF with their experimental results and discuss the benefits and drawbacks of each variant through the real-world application.
Legal artificial intelligence (LegalAI) aims to benefit legal systems with the technology of artificial intelligence, especially natural language processing (NLP). Recently, inspired by the success of pre-trained language models (PLMs) in the generic domain, many LegalAI researchers devote their effort to apply PLMs to legal tasks. However, utilizing PLMs to address legal tasks is still challenging, as the legal documents usually consist of thousands of tokens, which is far longer than the length that mainstream PLMs can process. In this paper, we release the Longformer-based pre-trained language model, named as Lawformer, for Chinese legal long documents understanding. We evaluate Lawformer on a variety of LegalAI tasks, including judgment prediction, similar case retrieval, legal reading comprehension, and legal question answering. The experimental results demonstrate that our model can achieve promising improvement on tasks with long documents as inputs.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
