From 59f5740edef9ac629b2caf6babf1e06d14df92e7 Mon Sep 17 00:00:00 2001 From: Abhinav Sharma Date: Mon, 13 Nov 2017 17:13:49 +0530 Subject: [PATCH 1/2] improved upon the list of included stop_words --- spacy/lang/hi/stop_words.py | 62 ++++++++++++++++++++++++++++++++++++- 1 file changed, 61 insertions(+), 1 deletion(-) diff --git a/spacy/lang/hi/stop_words.py b/spacy/lang/hi/stop_words.py index 2ff27c015..370060c51 100644 --- a/spacy/lang/hi/stop_words.py +++ b/spacy/lang/hi/stop_words.py @@ -5,14 +5,23 @@ from __future__ import unicode_literals # Source: https://github.com/taranjeet/hindi-tokenizer/blob/master/stopwords.txt STOP_WORDS = set(""" +अंदर अत +अदि +अप अपना +अपनि अपनी अपने +अभि अभी अंदर आदि आप +इंहिं +इंहें +इंहों +इतयादि इत्यादि इन इनका @@ -21,13 +30,19 @@ STOP_WORDS = set(""" इन्हों इस इसका +इसकि इसकी इसके इसमें +इसि इसी इसे +उंहिं +उंहें +उंहों उन उनका +उनकि उनकी उनके उनको @@ -36,13 +51,17 @@ STOP_WORDS = set(""" उन्हों उस उसके +उसि उसी उसे एक एवं एस +एसे ऐसे +ओर और +कइ कई कर करता @@ -53,14 +72,18 @@ STOP_WORDS = set(""" कहते कहा का +काफि काफ़ी कि +किंहें +किंहों कितना किन्हें किन्हों किया किर किस +किसि किसी किसे की @@ -68,27 +91,38 @@ STOP_WORDS = set(""" कुल के को +कोइ कोई +कोन +कोनसा कौन कौनसा गया घर जब जहाँ +जहां जा +जिंहें +जिंहों जितना +जिधर जिन जिन्हें जिन्हों जिस जिसे जीधर +जेसा +जेसे जैसा जैसे जो तक तब तरह +तिंहें +तिंहों तिन तिन्हें तिन्हों @@ -96,32 +130,41 @@ STOP_WORDS = set(""" तिसे तो था +थि थी थे दबारा +दवारा दिया दुसरा +दुसरे दूसरे दो द्वारा न -नके +नहिं नहीं ना +निचे निहायत नीचे ने पर पहले +पुरा पूरा पे फिर +बनि बनी +बहि बही बहुत बाद बाला बिलकुल +भि +भितर भी भीतर मगर @@ -131,11 +174,14 @@ STOP_WORDS = set(""" यदि यह यहाँ +यहां +यहि यही या यिह ये रखें +रवासा रहा रहे ऱ्वासा @@ -143,17 +189,24 @@ STOP_WORDS = set(""" लिये लेकिन व +वगेरह वग़ैरह +वरग वर्ग वह वहाँ +वहां +वहिं वहीं वाले वुह वे +वग़ैरह +संग सकता सकते सबसे +सभि सभी साथ साबुत @@ -162,16 +215,23 @@ STOP_WORDS = set(""" से सो संग +हि ही +हुअ हुआ +हुइ हुई हुए +हे +हें है हैं हो होता +होति होती होते होना होने + """.split()) From 4dd34058a2deb46386bf6d9627863b6d960db317 Mon Sep 17 00:00:00 2001 From: Abhinav Sharma Date: Mon, 13 Nov 2017 17:23:05 +0530 Subject: [PATCH 2/2] Create abhi18av.md --- .github/contributors/abhi18av.md | 106 +++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/abhi18av.md diff --git a/.github/contributors/abhi18av.md b/.github/contributors/abhi18av.md new file mode 100644 index 000000000..71a6671e9 --- /dev/null +++ b/.github/contributors/abhi18av.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI UG (haftungsbeschränkt)](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Abhinav Sharma | +| Company name (if applicable) | Fourtek I.T. Solutions Pvt. Ltd. | +| Title or role (if applicable) | Machine Learning Engineer | +| Date | 3 November 2017 | +| GitHub username | abhi18av | +| Website (optional) | https://abhi18av.github.io/ |