Questions tagged [information-retrieval]
Information Retrieval is an area of study concerning with retrieving documents, information or metadata from a collection of unstructured or semi-structured data.
139
questions
0
votes
1
answer
48
views
Fastest way to do Maximum Inner Product Search?
There have lots of $d-$dimension vectors, they combine a set $X$. We use an input query $q$. We need to find the $p$, which has the maximum inner product from the set $X$.
$$
p = \arg \max_{x \in ...
- 25
0
votes
0
answers
13
views
What options do I have when performing RAG on similarly phrased chunks?
I'm building a RAG pipeline to extract real estate phrases from excel documents. These phrases are short (2-5 words) and are often phrased differently.
I've manually added in different phrases to each ...
- 268
0
votes
0
answers
15
views
How to calucate recall at k when the number of relevant document is large?
In information retrieval, how to calculate r@k when the number of the relevant document is large? The formular is:
$
\text{Recall@K} = \frac{\text{True positive}}{\text{relevant document}}
$
If ...
- 33
1
vote
1
answer
2k
views
Splitting documents with langchain when a sentence straddles the a page break
I've been following this guide to Langchain: https://learn.deeplearning.ai/langchain-chat-with-your-data/lesson/3/document-splitting
It seems like the Langchain document loaders treat each page of a ...
- 153
0
votes
0
answers
26
views
Can I use faiss as retrieve on recommendation system?
I'm planning on using faiss to generate candidates and then lightgbm to rank the candidates.
I think about using E-commerce data, as most of the examples I see using faiss are textual data.
Is using ...
0
votes
0
answers
12
views
Add parameter efficient training in retrieval natural language processing
I am studying some paper with retrieval augmented generation and parameter efficient work on NLP task, ex: adapter, prefix tuning, prompt ...
I wonder that can I get better performance with parameter-...
- 25
0
votes
1
answer
11
views
How to handle using input feature (clicks) when it is used in target too?
I am trying to create a ranking model, where I am thinking about creating ground truth based on clicks by user. But at same time past clicks made by users seems like a vital input feature too. Any ...
- 1
0
votes
0
answers
8
views
Given a Query set, find elements in a pool that are similar to the elements in the query set
I had some curiosity and I was wondering if anyone could shed some light on this. So, let's say I have a query set $Q$ that consists of the following sets of words: {...
- 21
0
votes
1
answer
26
views
Survey on image retrieval datasets
I am on a survey about image retrieval datasets. I have found some, such as:
NUS-WIDE
Oxford5k
Oxford105k
Paris6k
MSCOCO
I have been way too confused about the detection metrics and the metrics they ...
- 3
0
votes
0
answers
357
views
Can BM25 be used as an embedding algorithm?
I'v studied about BM25 algorithm. Untill now, I couldn't find an implementation of BM25 to give me an embedding of a text like TfidfTransformer and ...
0
votes
0
answers
42
views
How to rank terms with bm25 and bo1 pipeline
In pyTerrier I have list of single terms. For example (I choose those tokens to be as relevant as possible and as irrelevant as possible to enhance the effect):
...
- 101
1
vote
1
answer
27
views
Empirical indications regarding demanded skills and tasks of data science jobs?
I am wondering if there are is any information about the current (and prospected) shares in skills required for advertised/existing data science jobs. This includes of course also the concrete tasks ...
- 111
1
vote
1
answer
125
views
How to add significance weighting in user based collaborative filtering
I have been learning about recommender systems these past days. More specifically about the collaborative filtering. While exploring I found that it can be useful to use "significance weighting&...
- 31
2
votes
1
answer
293
views
Why is accuracy not a useful measure for information retrieval problems?
I have been studying about information retrieval and recommender systems. While reading about it I found that accuracy not a useful measure in information retrieval.
I understand that, accuracy might ...
- 31
1
vote
0
answers
148
views
information retrieval vs recommendation system
Apologizes in advance, if this question is so basic,
Problem:
I have read this paper and noticed that Information Retrieval can be identified as a field of study whereas Recommender Systems are a ...
- 151
1
vote
0
answers
32
views
Optimizing Rank Aggregation of Two Different Methods in Information Retrieval
As the title suggests, I would like to train a rank-aggregating model. My target problem is to rank text2s from a database as best as possible to a given query, <...
- 11
1
vote
1
answer
74
views
Effectiveness of tf-idf on documents with repeated keywords
I was doing some ML reading and came upon tf-idf. The tf portion counts the relative frequency of a relevant word in a document, while idf measures how common or rare a word is across the corpus.
The ...
0
votes
1
answer
25
views
What method/algorithm to use to extract information from project documents about objectives, activities, and other variables?
I'm more-or-less new to NLP so assume little existing knowledge! But I have strong coding skills in R and to a lesser extent Python.
We're interested in extracting key information about objectives, ...
- 1
1
vote
2
answers
334
views
How to interpret rank output from BM25?
I'm using the FTS5 functionality in Sqlite3 to compute a search rank, which uses BM25. Maybe I'm just not seeing it, but I can't find any description of how to actually interpret BM25's output ranking....
- 121
0
votes
1
answer
235
views
What did Sentence-Bert return here?
I used sentence bert to embed sentences from this tutorial https://www.sbert.net/docs/pretrained_models.html
...
- 165
1
vote
1
answer
47
views
A way to perform voting and select a candidate based on nearest neighbours
I'm working on a project where I use FAISS to retrieve n neighbouring vectors based on a query vector. The data in question is textual and is being embedded by using a machine learning model to create ...
- 111
1
vote
1
answer
637
views
How can I implement lambda-mart with lightgbm?
I have a learning to rank task at hand and I want to use the lightgbm implementation of LambdaMART. I'm also following this notebook.
...
- 686
1
vote
1
answer
138
views
Can I use Sentence-Bert to embed event triples?
I extracted event triples from sentences using OpenIE. Can I concatenate the components in the event triple to make it a sentence and use Sentence-Bert to embed it?
It seems no one has done this way ...
- 165
2
votes
1
answer
134
views
How "similarity" is measured in image retrieval?
I know what content based image retireval is. I have read this and this
as one of them says: "given a query images, get a rank list that are most similar to the query image, based on the content ...
- 131
2
votes
1
answer
234
views
How to determine the "total number of relevant documents" in calculatiion of Recall in Precision and Recall if it's not known? Can it be estimated?
On Wikipedia there is a practical example of calculating Precision and Recall:
When a search engine returns 30 pages, only 20 of which are relevant,
while failing to return 40 additional relevant ...
- 131
1
vote
0
answers
30
views
Extracting information from bills, tax statements, etc: What ML model to use?
I have a bunch of documents such as bank statements, utilities bills, personal expenditure invoices, etc. The document types range is very broad. Some of these files are saved as pictures, others as ...
2
votes
0
answers
450
views
Is there a Mean Average Recall for Item Retrieval/ Recommendation Systems?
Mean Average Precision for Information retrieval is computed using Average Precision @ k (AP@k).
AP@k is measured by first computing Precision @ k (P@k) and then averaging the P@k only for the k's ...
- 121
1
vote
0
answers
52
views
Difference between the architectures of semantic and instance segmentation
My question is about the difference between the architectures of semantic segmentation and instance segmentation models. So, as far as I understand, a semantic segmentation model is making pixel-wise ...
- 111
0
votes
1
answer
5k
views
How to extract details (educational details, exp details etc.) from a resume?
I am trying to build a resume parser which can extract details such as Name, Address, Education details (degree name, college name, university name, course duration), Experience details (designation, ...
- 197
1
vote
1
answer
121
views
Document ranking on a web scraped dataset without any labelled data
I want to create a document ranking model which returns similar rows in the dataset for a sample query. The text in this corpus is standard english but without any labels (ie no query-related ...
- 11
0
votes
0
answers
30
views
How do I verify and test a machine learning model against reality during time?
As a software engineers we familiar with a concept of testing (unit, integration, e2e) Tests give us a level of confidence about the code and changes in our code.
Looks like for ML the "code"...
1
vote
0
answers
35
views
Approximate maximum dot product between a vector and set of vectors using only a single vector representation for the latter
If we have a vector $q$ and a set of vectors $D = \{d_1, d_2, ..., d_l\}$ is there a way to create functions $QF$ and $DF$ such that $QF(q)^TDF(D) \approx \max_i(q^Td_i)$ ?
Use case:
I want to build ...
- 11
0
votes
0
answers
20
views
How is a textual search engine able to recognize subwords from words?
I am interested to know how information retrieval systems are able to consider relevant subwords from a main search word when performing a keyword search. For example, the word ...
- 1
3
votes
1
answer
110
views
Origin of the Boolean Model of Information Retrieval
Simple question, but I can't really find the answer to that: Who "invented" Boolean Retrieval? Of course, I assume that the concept grew over time, but is there a paper or publication that ...
- 81
1
vote
1
answer
437
views
What is the difference between Okapi bm25 and NMSLIB?
I was trying to make a search system and then I got to know about Okapi bm25 which is a ranking function like tf-idf. You can make an index of your corpus and later ...
- 113
0
votes
1
answer
50
views
How to stem plural words properly?
I'm looking for a way to avoid removing ending s when s isn't a suffix. In order to do that, I first check if a word exists in ...
- 101
1
vote
1
answer
56
views
Evaluation of recommendation systems
I have developed a content-based recommendation system and it is working fine. The input is a set of documents={d1,d2,d3,...,dn} and the output will be Top N similar documents for a given document ...
- 159
3
votes
1
answer
366
views
Evaluation metric for Information retrieval system
I am currently reading Semantic Product Search paper published by Amazon. They are using two evaluation subtasks matching and ranking. In matching, they tune the model hyperparameters to
maximize ...
- 2,041
-1
votes
1
answer
30
views
How to find correlated knowledge among different documents? [closed]
Say I have a sequence of documents clicked by a user, how can I mine the identical or semanticly similar word/knowledge/phrases shared among different documents?
Maybe someone can give a paper or ...
- 103
1
vote
1
answer
538
views
Using BM25 to rank words
How effective is it to use BM25 to rank words, to be more specific i have a dictionary of words and i want to rank only words in a document that are also in my dictionary. I want to rank all words in ...
- 41
1
vote
0
answers
594
views
Merging (intersecting) more than two posting list in linear time
The intersecting algorithm for two posting lists implemented below:
...
- 141
1
vote
0
answers
22
views
Effecient Feature Searching
I have got multiple features(descriptor, vector with elements of natural or real number) from a single image, which need to be searched against many image with multiple features. It is a problem from ...
- 111
1
vote
0
answers
84
views
Using transformers for information extraction
Task
I am trying to do some information extraction on earnings reports. I am trying to extract certain metrics, e.g. net sales for quarters. The earnings reports differ quite a lot in how they are ...
- 111
4
votes
2
answers
768
views
Building a tag-based recommendation engine given a set of user tags?
Basically, the idea is to have users following tags on the site, so each users has a set of tags they are following. And then there is a document collection where each document in the collection has a ...
1
vote
1
answer
27
views
Domain scoring based on ranking
I am a computer science student working on a small information retrieval project. I have a dictionary with a domain as a key and it's ranking as value.
Based on that ranking, I need to score every ...
- 11
4
votes
1
answer
132
views
Visualizing F-score differences in information extraction
I have several corpora and NLP systems (including a few merge ensembles of output of these systems combined in unions and intersections) with which I have extracted the annotation span sets {(begin, ...
- 201
1
vote
0
answers
229
views
Meaningful Information retrieval and question answering for unstructured data - Is it even possible?
Hello good NLP people,
I am working on a task that gradually seems not solvable for me. My data-set consists of long, messy, unstructured documents (pdfs, doc, docx, scans with tables, graphs, text, ...
- 111
3
votes
1
answer
338
views
Evaluating a IR system (Precision and Recall)
I am studying by now IR system, in the field of valuation of IR system outputs related to a specific query but I need some help to understand it properly.
My book states that when an IR system has ...
9
votes
1
answer
3k
views
How can you build a model that extracts data out from receipts?
I'm trying to build a model that is capable of identifying information on receipts and invoices.
I have used google cloud vision api for text extraction from the receipt but the problem is it just ...
- 347
4
votes
1
answer
81
views
How is "relevance" defined in information retrieval outside the context of systems with user feedback?
I've seen information retrieval systems that return some results from a query, and then the user rates these results as either "relevant" or "not relevant".
What can you do if you do not have user ...
- 53